|
--- |
|
base_model: SQAI/streetlight_sql_embedding |
|
datasets: [] |
|
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 |
|
- generated_from_trainer |
|
- dataset_size:2161 |
|
- loss:MatryoshkaLoss |
|
- loss:MultipleNegativesRankingLoss |
|
widget: |
|
- source_sentence: longitude of streetlight |
|
sentences: |
|
- '"What is the recent status of the streetlight at the given longitude, considering |
|
the current overload conditions?"' |
|
- '"Has there been any recent failure in the metering components of the streetlights |
|
affecting data reporting, and was the control mode switch identifier used for |
|
the changes?"' |
|
- '"Can you tell me when was the most recent instance when the current exceeded |
|
the safe operating threshold, causing a streetlight failure?"' |
|
- source_sentence: Ambient light level detected by the streetlight, measured in lux |
|
sentences: |
|
- '"What is the count of how many times the most recent streetlight failure has |
|
been switched on before the error occurred?"' |
|
- '"What is the recent data on maximum load current indicating potential risk and |
|
any recent communication issues with the lux sensors?"' |
|
- '"What is the recent dimming schedule applied, the detected ambient light level |
|
in lux, and were there any recent issues or failures with the driver of the streetlight?"' |
|
- source_sentence: Timestamp of the latest data recorded or action performed by the |
|
streetlight |
|
sentences: |
|
- '"What is the recent failure rate of the relay responsible for operating the DALI |
|
dimming protocol in our streetlights?"' |
|
- '"Can you provide the recent instances where the current drawn by the streetlights |
|
was lower than expected, sorted by the unique streetlight identifier and street |
|
name?"' |
|
- '"What was the most recent threshold level set to stop recording flickering events |
|
using the SIM card code in the streetlight?"' |
|
- source_sentence: Current exceeds the safe operating threshold for the streetlight |
|
(failure) |
|
sentences: |
|
- '"What is the hardware version of the recent streetlight experiencing faults in |
|
its lux module affecting light level sensing and control?"' |
|
- '"Can you provide the recent instances where the current drawn by the streetlights |
|
was lower than expected, sorted by the unique streetlight identifier and street |
|
name?"' |
|
- '"Can you identify the most recent instance when the power under load was higher |
|
than normal, possibly indicating inefficiency or a fault, and concurrently, the |
|
voltage exceeded the safe operating levels for the streetlights?"' |
|
- source_sentence: Voltage supplied is below the safe operating level for the streetlight |
|
(failure) |
|
sentences: |
|
- '"What is the recent AC voltage supply to the streetlight and the SIM card code |
|
used for its cellular network communication?"' |
|
- '"What was the most recent threshold level set to stop recording flickering events |
|
using the SIM card code in the streetlight?"' |
|
- '"What is the most recent internal temperature reading for the operating conditions |
|
of the streetlight?"' |
|
model-index: |
|
- name: BGE base Financial Matryoshka |
|
results: |
|
- task: |
|
type: information-retrieval |
|
name: Information Retrieval |
|
dataset: |
|
name: dim 768 |
|
type: dim_768 |
|
metrics: |
|
- type: cosine_accuracy@1 |
|
value: 0.004149377593360996 |
|
name: Cosine Accuracy@1 |
|
- type: cosine_accuracy@3 |
|
value: 0.02074688796680498 |
|
name: Cosine Accuracy@3 |
|
- type: cosine_accuracy@5 |
|
value: 0.04149377593360996 |
|
name: Cosine Accuracy@5 |
|
- type: cosine_accuracy@10 |
|
value: 0.06224066390041494 |
|
name: Cosine Accuracy@10 |
|
- type: cosine_precision@1 |
|
value: 0.004149377593360996 |
|
name: Cosine Precision@1 |
|
- type: cosine_precision@3 |
|
value: 0.006915629322268326 |
|
name: Cosine Precision@3 |
|
- type: cosine_precision@5 |
|
value: 0.008298755186721992 |
|
name: Cosine Precision@5 |
|
- type: cosine_precision@10 |
|
value: 0.006224066390041493 |
|
name: Cosine Precision@10 |
|
- type: cosine_recall@1 |
|
value: 0.004149377593360996 |
|
name: Cosine Recall@1 |
|
- type: cosine_recall@3 |
|
value: 0.02074688796680498 |
|
name: Cosine Recall@3 |
|
- type: cosine_recall@5 |
|
value: 0.04149377593360996 |
|
name: Cosine Recall@5 |
|
- type: cosine_recall@10 |
|
value: 0.06224066390041494 |
|
name: Cosine Recall@10 |
|
- type: cosine_ndcg@10 |
|
value: 0.028846821098581887 |
|
name: Cosine Ndcg@10 |
|
- type: cosine_mrr@10 |
|
value: 0.018665612856484225 |
|
name: Cosine Mrr@10 |
|
- type: cosine_map@100 |
|
value: 0.024320046307682447 |
|
name: Cosine Map@100 |
|
- task: |
|
type: information-retrieval |
|
name: Information Retrieval |
|
dataset: |
|
name: dim 512 |
|
type: dim_512 |
|
metrics: |
|
- type: cosine_accuracy@1 |
|
value: 0.004149377593360996 |
|
name: Cosine Accuracy@1 |
|
- type: cosine_accuracy@3 |
|
value: 0.02074688796680498 |
|
name: Cosine Accuracy@3 |
|
- type: cosine_accuracy@5 |
|
value: 0.04149377593360996 |
|
name: Cosine Accuracy@5 |
|
- type: cosine_accuracy@10 |
|
value: 0.06224066390041494 |
|
name: Cosine Accuracy@10 |
|
- type: cosine_precision@1 |
|
value: 0.004149377593360996 |
|
name: Cosine Precision@1 |
|
- type: cosine_precision@3 |
|
value: 0.006915629322268326 |
|
name: Cosine Precision@3 |
|
- type: cosine_precision@5 |
|
value: 0.008298755186721992 |
|
name: Cosine Precision@5 |
|
- type: cosine_precision@10 |
|
value: 0.006224066390041493 |
|
name: Cosine Precision@10 |
|
- type: cosine_recall@1 |
|
value: 0.004149377593360996 |
|
name: Cosine Recall@1 |
|
- type: cosine_recall@3 |
|
value: 0.02074688796680498 |
|
name: Cosine Recall@3 |
|
- type: cosine_recall@5 |
|
value: 0.04149377593360996 |
|
name: Cosine Recall@5 |
|
- type: cosine_recall@10 |
|
value: 0.06224066390041494 |
|
name: Cosine Recall@10 |
|
- type: cosine_ndcg@10 |
|
value: 0.028846821098581887 |
|
name: Cosine Ndcg@10 |
|
- type: cosine_mrr@10 |
|
value: 0.018665612856484225 |
|
name: Cosine Mrr@10 |
|
- type: cosine_map@100 |
|
value: 0.024320046307682447 |
|
name: Cosine Map@100 |
|
- task: |
|
type: information-retrieval |
|
name: Information Retrieval |
|
dataset: |
|
name: dim 256 |
|
type: dim_256 |
|
metrics: |
|
- type: cosine_accuracy@1 |
|
value: 0.008298755186721992 |
|
name: Cosine Accuracy@1 |
|
- type: cosine_accuracy@3 |
|
value: 0.02074688796680498 |
|
name: Cosine Accuracy@3 |
|
- type: cosine_accuracy@5 |
|
value: 0.04149377593360996 |
|
name: Cosine Accuracy@5 |
|
- type: cosine_accuracy@10 |
|
value: 0.058091286307053944 |
|
name: Cosine Accuracy@10 |
|
- type: cosine_precision@1 |
|
value: 0.008298755186721992 |
|
name: Cosine Precision@1 |
|
- type: cosine_precision@3 |
|
value: 0.006915629322268326 |
|
name: Cosine Precision@3 |
|
- type: cosine_precision@5 |
|
value: 0.008298755186721992 |
|
name: Cosine Precision@5 |
|
- type: cosine_precision@10 |
|
value: 0.0058091286307053935 |
|
name: Cosine Precision@10 |
|
- type: cosine_recall@1 |
|
value: 0.008298755186721992 |
|
name: Cosine Recall@1 |
|
- type: cosine_recall@3 |
|
value: 0.02074688796680498 |
|
name: Cosine Recall@3 |
|
- type: cosine_recall@5 |
|
value: 0.04149377593360996 |
|
name: Cosine Recall@5 |
|
- type: cosine_recall@10 |
|
value: 0.058091286307053944 |
|
name: Cosine Recall@10 |
|
- type: cosine_ndcg@10 |
|
value: 0.02917470145123319 |
|
name: Cosine Ndcg@10 |
|
- type: cosine_mrr@10 |
|
value: 0.020424158598432458 |
|
name: Cosine Mrr@10 |
|
- type: cosine_map@100 |
|
value: 0.02622693528356527 |
|
name: Cosine Map@100 |
|
- task: |
|
type: information-retrieval |
|
name: Information Retrieval |
|
dataset: |
|
name: dim 128 |
|
type: dim_128 |
|
metrics: |
|
- type: cosine_accuracy@1 |
|
value: 0.008298755186721992 |
|
name: Cosine Accuracy@1 |
|
- type: cosine_accuracy@3 |
|
value: 0.02074688796680498 |
|
name: Cosine Accuracy@3 |
|
- type: cosine_accuracy@5 |
|
value: 0.03734439834024896 |
|
name: Cosine Accuracy@5 |
|
- type: cosine_accuracy@10 |
|
value: 0.05394190871369295 |
|
name: Cosine Accuracy@10 |
|
- type: cosine_precision@1 |
|
value: 0.008298755186721992 |
|
name: Cosine Precision@1 |
|
- type: cosine_precision@3 |
|
value: 0.006915629322268326 |
|
name: Cosine Precision@3 |
|
- type: cosine_precision@5 |
|
value: 0.007468879668049794 |
|
name: Cosine Precision@5 |
|
- type: cosine_precision@10 |
|
value: 0.005394190871369295 |
|
name: Cosine Precision@10 |
|
- type: cosine_recall@1 |
|
value: 0.008298755186721992 |
|
name: Cosine Recall@1 |
|
- type: cosine_recall@3 |
|
value: 0.02074688796680498 |
|
name: Cosine Recall@3 |
|
- type: cosine_recall@5 |
|
value: 0.03734439834024896 |
|
name: Cosine Recall@5 |
|
- type: cosine_recall@10 |
|
value: 0.05394190871369295 |
|
name: Cosine Recall@10 |
|
- type: cosine_ndcg@10 |
|
value: 0.027438863848135625 |
|
name: Cosine Ndcg@10 |
|
- type: cosine_mrr@10 |
|
value: 0.019311071593229267 |
|
name: Cosine Mrr@10 |
|
- type: cosine_map@100 |
|
value: 0.02603525046406888 |
|
name: Cosine Map@100 |
|
- task: |
|
type: information-retrieval |
|
name: Information Retrieval |
|
dataset: |
|
name: dim 64 |
|
type: dim_64 |
|
metrics: |
|
- type: cosine_accuracy@1 |
|
value: 0.008298755186721992 |
|
name: Cosine Accuracy@1 |
|
- type: cosine_accuracy@3 |
|
value: 0.012448132780082987 |
|
name: Cosine Accuracy@3 |
|
- type: cosine_accuracy@5 |
|
value: 0.029045643153526972 |
|
name: Cosine Accuracy@5 |
|
- type: cosine_accuracy@10 |
|
value: 0.05394190871369295 |
|
name: Cosine Accuracy@10 |
|
- type: cosine_precision@1 |
|
value: 0.008298755186721992 |
|
name: Cosine Precision@1 |
|
- type: cosine_precision@3 |
|
value: 0.004149377593360996 |
|
name: Cosine Precision@3 |
|
- type: cosine_precision@5 |
|
value: 0.005809128630705394 |
|
name: Cosine Precision@5 |
|
- type: cosine_precision@10 |
|
value: 0.005394190871369295 |
|
name: Cosine Precision@10 |
|
- type: cosine_recall@1 |
|
value: 0.008298755186721992 |
|
name: Cosine Recall@1 |
|
- type: cosine_recall@3 |
|
value: 0.012448132780082987 |
|
name: Cosine Recall@3 |
|
- type: cosine_recall@5 |
|
value: 0.029045643153526972 |
|
name: Cosine Recall@5 |
|
- type: cosine_recall@10 |
|
value: 0.05394190871369295 |
|
name: Cosine Recall@10 |
|
- type: cosine_ndcg@10 |
|
value: 0.025512460997908278 |
|
name: Cosine Ndcg@10 |
|
- type: cosine_mrr@10 |
|
value: 0.017038793387341104 |
|
name: Cosine Mrr@10 |
|
- type: cosine_map@100 |
|
value: 0.02259750227693111 |
|
name: Cosine Map@100 |
|
--- |
|
|
|
# BGE base Financial Matryoshka |
|
|
|
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [SQAI/streetlight_sql_embedding](https://huggingface.co/SQAI/streetlight_sql_embedding). 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:** [SQAI/streetlight_sql_embedding](https://huggingface.co/SQAI/streetlight_sql_embedding) <!-- at revision de1e1a4c2afb3f9040c5f19953077d9fca76ae90 --> |
|
- **Maximum Sequence Length:** 512 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': 512, 'do_lower_case': True}) with Transformer model: BertModel |
|
(1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True}) |
|
(2): Normalize() |
|
) |
|
``` |
|
|
|
## Usage |
|
|
|
### Direct Usage (Sentence Transformers) |
|
|
|
First install the Sentence Transformers library: |
|
|
|
```bash |
|
pip install -U sentence-transformers |
|
``` |
|
|
|
Then you can load this model and run inference. |
|
```python |
|
from sentence_transformers import SentenceTransformer |
|
|
|
# Download from the 🤗 Hub |
|
model = SentenceTransformer("SQAI/streetlight_sql_embedding2") |
|
# Run inference |
|
sentences = [ |
|
'Voltage supplied is below the safe operating level for the streetlight (failure)', |
|
'"What is the recent AC voltage supply to the streetlight and the SIM card code used for its cellular network communication?"', |
|
'"What was the most recent threshold level set to stop recording flickering events using the SIM card code in the streetlight?"', |
|
] |
|
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_768` |
|
* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) |
|
|
|
| Metric | Value | |
|
|:--------------------|:-----------| |
|
| cosine_accuracy@1 | 0.0041 | |
|
| cosine_accuracy@3 | 0.0207 | |
|
| cosine_accuracy@5 | 0.0415 | |
|
| cosine_accuracy@10 | 0.0622 | |
|
| cosine_precision@1 | 0.0041 | |
|
| cosine_precision@3 | 0.0069 | |
|
| cosine_precision@5 | 0.0083 | |
|
| cosine_precision@10 | 0.0062 | |
|
| cosine_recall@1 | 0.0041 | |
|
| cosine_recall@3 | 0.0207 | |
|
| cosine_recall@5 | 0.0415 | |
|
| cosine_recall@10 | 0.0622 | |
|
| cosine_ndcg@10 | 0.0288 | |
|
| cosine_mrr@10 | 0.0187 | |
|
| **cosine_map@100** | **0.0243** | |
|
|
|
#### Information Retrieval |
|
* Dataset: `dim_512` |
|
* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) |
|
|
|
| Metric | Value | |
|
|:--------------------|:-----------| |
|
| cosine_accuracy@1 | 0.0041 | |
|
| cosine_accuracy@3 | 0.0207 | |
|
| cosine_accuracy@5 | 0.0415 | |
|
| cosine_accuracy@10 | 0.0622 | |
|
| cosine_precision@1 | 0.0041 | |
|
| cosine_precision@3 | 0.0069 | |
|
| cosine_precision@5 | 0.0083 | |
|
| cosine_precision@10 | 0.0062 | |
|
| cosine_recall@1 | 0.0041 | |
|
| cosine_recall@3 | 0.0207 | |
|
| cosine_recall@5 | 0.0415 | |
|
| cosine_recall@10 | 0.0622 | |
|
| cosine_ndcg@10 | 0.0288 | |
|
| cosine_mrr@10 | 0.0187 | |
|
| **cosine_map@100** | **0.0243** | |
|
|
|
#### 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 | 0.0083 | |
|
| cosine_accuracy@3 | 0.0207 | |
|
| cosine_accuracy@5 | 0.0415 | |
|
| cosine_accuracy@10 | 0.0581 | |
|
| cosine_precision@1 | 0.0083 | |
|
| cosine_precision@3 | 0.0069 | |
|
| cosine_precision@5 | 0.0083 | |
|
| cosine_precision@10 | 0.0058 | |
|
| cosine_recall@1 | 0.0083 | |
|
| cosine_recall@3 | 0.0207 | |
|
| cosine_recall@5 | 0.0415 | |
|
| cosine_recall@10 | 0.0581 | |
|
| cosine_ndcg@10 | 0.0292 | |
|
| cosine_mrr@10 | 0.0204 | |
|
| **cosine_map@100** | **0.0262** | |
|
|
|
#### 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 | 0.0083 | |
|
| cosine_accuracy@3 | 0.0207 | |
|
| cosine_accuracy@5 | 0.0373 | |
|
| cosine_accuracy@10 | 0.0539 | |
|
| cosine_precision@1 | 0.0083 | |
|
| cosine_precision@3 | 0.0069 | |
|
| cosine_precision@5 | 0.0075 | |
|
| cosine_precision@10 | 0.0054 | |
|
| cosine_recall@1 | 0.0083 | |
|
| cosine_recall@3 | 0.0207 | |
|
| cosine_recall@5 | 0.0373 | |
|
| cosine_recall@10 | 0.0539 | |
|
| cosine_ndcg@10 | 0.0274 | |
|
| cosine_mrr@10 | 0.0193 | |
|
| **cosine_map@100** | **0.026** | |
|
|
|
#### 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 | 0.0083 | |
|
| cosine_accuracy@3 | 0.0124 | |
|
| cosine_accuracy@5 | 0.029 | |
|
| cosine_accuracy@10 | 0.0539 | |
|
| cosine_precision@1 | 0.0083 | |
|
| cosine_precision@3 | 0.0041 | |
|
| cosine_precision@5 | 0.0058 | |
|
| cosine_precision@10 | 0.0054 | |
|
| cosine_recall@1 | 0.0083 | |
|
| cosine_recall@3 | 0.0124 | |
|
| cosine_recall@5 | 0.029 | |
|
| cosine_recall@10 | 0.0539 | |
|
| cosine_ndcg@10 | 0.0255 | |
|
| cosine_mrr@10 | 0.017 | |
|
| **cosine_map@100** | **0.0226** | |
|
|
|
<!-- |
|
## 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: 2,161 training samples |
|
* Columns: <code>positive</code> and <code>anchor</code> |
|
* Approximate statistics based on the first 1000 samples: |
|
| | positive | anchor | |
|
|:--------|:---------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------| |
|
| type | string | string | |
|
| details | <ul><li>min: 6 tokens</li><li>mean: 14.3 tokens</li><li>max: 20 tokens</li></ul> | <ul><li>min: 15 tokens</li><li>mean: 32.58 tokens</li><li>max: 54 tokens</li></ul> | |
|
* Samples: |
|
| positive | anchor | |
|
|:-----------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| |
|
| <code>Lower lux level below which additional lighting may be necessary</code> | <code>"What are the recent faults found in the lux module that affect light level control, in relation to the default dimming level of the streetlights and the control mode switch identifier used for changing settings?"</code> | |
|
| <code>Current dimming level of the streetlight in operation</code> | <code>"Can the operator managing the streetlights provide the most recent update on the streetlight that is currently below the expected range and unable to connect to the network for remote management?"</code> | |
|
| <code>Upper voltage limit considered safe and efficient for streetlight operation</code> | <code>"Can you provide any recent potential failures of a streetlight group due to unusually high voltage under load or intermittent flashing, within the southernmost geographic area?"</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 |
|
} |
|
``` |
|
|
|
### Evaluation Dataset |
|
|
|
#### Unnamed Dataset |
|
|
|
|
|
* Size: 241 evaluation samples |
|
* Columns: <code>positive</code> and <code>anchor</code> |
|
* Approximate statistics based on the first 1000 samples: |
|
| | positive | anchor | |
|
|:--------|:----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------| |
|
| type | string | string | |
|
| details | <ul><li>min: 6 tokens</li><li>mean: 14.31 tokens</li><li>max: 20 tokens</li></ul> | <ul><li>min: 17 tokens</li><li>mean: 31.03 tokens</li><li>max: 54 tokens</li></ul> | |
|
* Samples: |
|
| positive | anchor | |
|
|:-------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------| |
|
| <code>Timestamp of the latest data recorded or action performed by the streetlight</code> | <code>"What was the most recent threshold level set to stop recording flickering events using the SIM card code in the streetlight?"</code> | |
|
| <code>Maximum longitude of the geographic area covered by the group of streetlights</code> | <code>"What is the recent power usage in watts for the oldest streetlight on the street with maximum longitude?"</code> | |
|
| <code>Current dimming level of the streetlight in operation</code> | <code>"What is the most recent dimming level of the streetlight?"</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`: 16 |
|
- `gradient_accumulation_steps`: 16 |
|
- `learning_rate`: 1e-05 |
|
- `weight_decay`: 0.03 |
|
- `num_train_epochs`: 75 |
|
- `lr_scheduler_type`: cosine |
|
- `warmup_ratio`: 0.2 |
|
- `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`: 16 |
|
- `per_gpu_train_batch_size`: None |
|
- `per_gpu_eval_batch_size`: None |
|
- `gradient_accumulation_steps`: 16 |
|
- `eval_accumulation_steps`: None |
|
- `learning_rate`: 1e-05 |
|
- `weight_decay`: 0.03 |
|
- `adam_beta1`: 0.9 |
|
- `adam_beta2`: 0.999 |
|
- `adam_epsilon`: 1e-08 |
|
- `max_grad_norm`: 1.0 |
|
- `num_train_epochs`: 75 |
|
- `max_steps`: -1 |
|
- `lr_scheduler_type`: cosine |
|
- `lr_scheduler_kwargs`: {} |
|
- `warmup_ratio`: 0.2 |
|
- `warmup_steps`: 0 |
|
- `log_level`: passive |
|
- `log_level_replica`: warning |
|
- `log_on_each_node`: True |
|
- `logging_nan_inf_filter`: True |
|
- `save_safetensors`: True |
|
- `save_on_each_node`: False |
|
- `save_only_model`: False |
|
- `restore_callback_states_from_checkpoint`: False |
|
- `no_cuda`: False |
|
- `use_cpu`: False |
|
- `use_mps_device`: False |
|
- `seed`: 42 |
|
- `data_seed`: None |
|
- `jit_mode_eval`: False |
|
- `use_ipex`: False |
|
- `bf16`: True |
|
- `fp16`: False |
|
- `fp16_opt_level`: O1 |
|
- `half_precision_backend`: auto |
|
- `bf16_full_eval`: False |
|
- `fp16_full_eval`: False |
|
- `tf32`: True |
|
- `local_rank`: 0 |
|
- `ddp_backend`: None |
|
- `tpu_num_cores`: None |
|
- `tpu_metrics_debug`: False |
|
- `debug`: [] |
|
- `dataloader_drop_last`: False |
|
- `dataloader_num_workers`: 0 |
|
- `dataloader_prefetch_factor`: None |
|
- `past_index`: -1 |
|
- `disable_tqdm`: False |
|
- `remove_unused_columns`: True |
|
- `label_names`: None |
|
- `load_best_model_at_end`: True |
|
- `ignore_data_skip`: False |
|
- `fsdp`: [] |
|
- `fsdp_min_num_params`: 0 |
|
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False} |
|
- `fsdp_transformer_layer_cls_to_wrap`: None |
|
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None} |
|
- `deepspeed`: None |
|
- `label_smoothing_factor`: 0.0 |
|
- `optim`: adamw_torch_fused |
|
- `optim_args`: None |
|
- `adafactor`: False |
|
- `group_by_length`: False |
|
- `length_column_name`: length |
|
- `ddp_find_unused_parameters`: None |
|
- `ddp_bucket_cap_mb`: None |
|
- `ddp_broadcast_buffers`: False |
|
- `dataloader_pin_memory`: True |
|
- `dataloader_persistent_workers`: False |
|
- `skip_memory_metrics`: True |
|
- `use_legacy_prediction_loop`: False |
|
- `push_to_hub`: False |
|
- `resume_from_checkpoint`: None |
|
- `hub_model_id`: None |
|
- `hub_strategy`: every_save |
|
- `hub_private_repo`: False |
|
- `hub_always_push`: False |
|
- `gradient_checkpointing`: False |
|
- `gradient_checkpointing_kwargs`: None |
|
- `include_inputs_for_metrics`: False |
|
- `eval_do_concat_batches`: True |
|
- `fp16_backend`: auto |
|
- `push_to_hub_model_id`: None |
|
- `push_to_hub_organization`: None |
|
- `mp_parameters`: |
|
- `auto_find_batch_size`: False |
|
- `full_determinism`: False |
|
- `torchdynamo`: None |
|
- `ray_scope`: last |
|
- `ddp_timeout`: 1800 |
|
- `torch_compile`: False |
|
- `torch_compile_backend`: None |
|
- `torch_compile_mode`: None |
|
- `dispatch_batches`: None |
|
- `split_batches`: None |
|
- `include_tokens_per_second`: False |
|
- `include_num_input_tokens_seen`: False |
|
- `neftune_noise_alpha`: None |
|
- `optim_target_modules`: None |
|
- `batch_eval_metrics`: False |
|
- `batch_sampler`: no_duplicates |
|
- `multi_dataset_batch_sampler`: proportional |
|
|
|
</details> |
|
|
|
### Training Logs |
|
<details><summary>Click to expand</summary> |
|
|
|
| Epoch | Step | Training Loss | loss | dim_128_cosine_map@100 | dim_256_cosine_map@100 | dim_512_cosine_map@100 | dim_64_cosine_map@100 | dim_768_cosine_map@100 | |
|
|:-----------:|:-------:|:-------------:|:----------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|:----------------------:| |
|
| 0.2353 | 1 | 11.247 | - | - | - | - | - | - | |
|
| 0.4706 | 2 | 11.4455 | - | - | - | - | - | - | |
|
| 0.7059 | 3 | 11.5154 | - | - | - | - | - | - | |
|
| 0.9412 | 4 | 10.4079 | - | - | - | - | - | - | |
|
| 1.1765 | 5 | 3.3256 | - | - | - | - | - | - | |
|
| 1.4118 | 6 | 3.812 | - | - | - | - | - | - | |
|
| 1.6471 | 7 | 4.0302 | - | - | - | - | - | - | |
|
| 1.8824 | 8 | 3.5832 | - | - | - | - | - | - | |
|
| 2.1176 | 9 | 3.9586 | - | - | - | - | - | - | |
|
| 2.3529 | 10 | 4.2835 | - | - | - | - | - | - | |
|
| 2.5882 | 11 | 1.6391 | 6.0237 | 0.0254 | 0.0354 | 0.0318 | 0.0230 | 0.0318 | |
|
| 1.0294 | 12 | 1.3873 | - | - | - | - | - | - | |
|
| 1.2647 | 13 | 11.1729 | - | - | - | - | - | - | |
|
| 1.5 | 14 | 11.1729 | - | - | - | - | - | - | |
|
| 1.7353 | 15 | 11.3334 | - | - | - | - | - | - | |
|
| 1.9706 | 16 | 9.1337 | - | - | - | - | - | - | |
|
| 2.2059 | 17 | 2.8674 | - | - | - | - | - | - | |
|
| 2.4412 | 18 | 3.9162 | - | - | - | - | - | - | |
|
| 2.6765 | 19 | 3.3378 | - | - | - | - | - | - | |
|
| 2.9118 | 20 | 3.5152 | - | - | - | - | - | - | |
|
| 3.1471 | 21 | 3.1655 | - | - | - | - | - | - | |
|
| 3.3824 | 22 | 3.5905 | - | - | - | - | - | - | |
|
| 3.6176 | 23 | 1.2027 | 5.5383 | 0.0265 | 0.0304 | 0.0291 | 0.0235 | 0.0291 | |
|
| 2.0588 | 24 | 2.5902 | - | - | - | - | - | - | |
|
| 2.2941 | 25 | 10.8776 | - | - | - | - | - | - | |
|
| 2.5294 | 26 | 10.7109 | - | - | - | - | - | - | |
|
| 2.7647 | 27 | 10.9662 | - | - | - | - | - | - | |
|
| 3.0 | 28 | 7.5032 | - | - | - | - | - | - | |
|
| 3.2353 | 29 | 1.9266 | - | - | - | - | - | - | |
|
| 3.4706 | 30 | 2.5007 | - | - | - | - | - | - | |
|
| 3.7059 | 31 | 2.2972 | - | - | - | - | - | - | |
|
| 3.9412 | 32 | 2.3428 | - | - | - | - | - | - | |
|
| 4.1765 | 33 | 2.4842 | - | - | - | - | - | - | |
|
| 4.4118 | 34 | 2.371 | - | - | - | - | - | - | |
|
| 4.6471 | 35 | 0.8811 | 5.0896 | 0.0261 | 0.0356 | 0.0324 | 0.0263 | 0.0324 | |
|
| 3.0882 | 36 | 3.8163 | - | - | - | - | - | - | |
|
| 3.3235 | 37 | 10.3601 | - | - | - | - | - | - | |
|
| 3.5588 | 38 | 9.8085 | - | - | - | - | - | - | |
|
| 3.7941 | 39 | 10.3201 | - | - | - | - | - | - | |
|
| 4.0294 | 40 | 5.7213 | - | - | - | - | - | - | |
|
| 4.2647 | 41 | 1.0641 | - | - | - | - | - | - | |
|
| 4.5 | 42 | 1.7557 | - | - | - | - | - | - | |
|
| 4.7353 | 43 | 1.534 | - | - | - | - | - | - | |
|
| 4.9706 | 44 | 1.2931 | - | - | - | - | - | - | |
|
| 5.2059 | 45 | 2.0569 | - | - | - | - | - | - | |
|
| 5.4412 | 46 | 1.6945 | - | - | - | - | - | - | |
|
| 5.6765 | 47 | 0.6985 | 4.8110 | 0.0267 | 0.0230 | 0.0343 | 0.0180 | 0.0343 | |
|
| 4.1176 | 48 | 4.8862 | - | - | - | - | - | - | |
|
| 4.3529 | 49 | 9.9427 | - | - | - | - | - | - | |
|
| 4.5882 | 50 | 9.7492 | - | - | - | - | - | - | |
|
| 4.8235 | 51 | 10.1616 | - | - | - | - | - | - | |
|
| 5.0588 | 52 | 4.3073 | - | - | - | - | - | - | |
|
| 5.2941 | 53 | 0.9089 | - | - | - | - | - | - | |
|
| 5.5294 | 54 | 1.2689 | - | - | - | - | - | - | |
|
| 5.7647 | 55 | 1.2875 | - | - | - | - | - | - | |
|
| 6.0 | 56 | 1.2756 | - | - | - | - | - | - | |
|
| 6.2353 | 57 | 1.6222 | - | - | - | - | - | - | |
|
| 6.4706 | 58 | 1.3049 | - | - | - | - | - | - | |
|
| 6.7059 | 59 | 0.3305 | 4.6562 | 0.0184 | 0.0327 | 0.0288 | 0.0190 | 0.0288 | |
|
| 5.1471 | 60 | 5.7286 | - | - | - | - | - | - | |
|
| 5.3824 | 61 | 9.7399 | - | - | - | - | - | - | |
|
| 5.6176 | 62 | 9.3036 | - | - | - | - | - | - | |
|
| 5.8529 | 63 | 9.6674 | - | - | - | - | - | - | |
|
| 6.0882 | 64 | 2.7979 | - | - | - | - | - | - | |
|
| 6.3235 | 65 | 0.4978 | - | - | - | - | - | - | |
|
| 6.5588 | 66 | 1.8006 | - | - | - | - | - | - | |
|
| 6.7941 | 67 | 1.098 | - | - | - | - | - | - | |
|
| 7.0294 | 68 | 1.3678 | - | - | - | - | - | - | |
|
| 7.2647 | 69 | 1.4648 | - | - | - | - | - | - | |
|
| 7.5 | 70 | 1.1826 | - | - | - | - | - | - | |
|
| 7.7353 | 71 | 0.0624 | 4.5802 | 0.0200 | 0.0208 | 0.0216 | 0.0231 | 0.0216 | |
|
| 6.1765 | 72 | 6.8322 | - | - | - | - | - | - | |
|
| 6.4118 | 73 | 9.3021 | - | - | - | - | - | - | |
|
| 6.6471 | 74 | 9.1494 | - | - | - | - | - | - | |
|
| 6.8824 | 75 | 9.631 | - | - | - | - | - | - | |
|
| 7.1176 | 76 | 1.661 | - | - | - | - | - | - | |
|
| 7.3529 | 77 | 0.2353 | - | - | - | - | - | - | |
|
| 7.5882 | 78 | 1.0663 | - | - | - | - | - | - | |
|
| 7.8235 | 79 | 0.6836 | - | - | - | - | - | - | |
|
| 8.0588 | 80 | 0.9921 | - | - | - | - | - | - | |
|
| 8.2941 | 81 | 1.6479 | - | - | - | - | - | - | |
|
| 8.5294 | 82 | 0.6713 | - | - | - | - | - | - | |
|
| 8.7647 | 83 | 0.0 | 4.5499 | 0.0209 | 0.0233 | 0.0249 | 0.0226 | 0.0249 | |
|
| 7.2059 | 84 | 7.775 | - | - | - | - | - | - | |
|
| 7.4412 | 85 | 9.0508 | - | - | - | - | - | - | |
|
| 7.6765 | 86 | 9.1417 | - | - | - | - | - | - | |
|
| 7.9118 | 87 | 8.9087 | - | - | - | - | - | - | |
|
| 8.1471 | 88 | 0.9757 | - | - | - | - | - | - | |
|
| 8.3824 | 89 | 0.7521 | - | - | - | - | - | - | |
|
| 8.6176 | 90 | 0.7292 | - | - | - | - | - | - | |
|
| 8.8529 | 91 | 0.6088 | - | - | - | - | - | - | |
|
| 9.0882 | 92 | 0.9514 | - | - | - | - | - | - | |
|
| 9.3235 | 93 | 1.435 | - | - | - | - | - | - | |
|
| 9.5588 | 94 | 0.3655 | - | - | - | - | - | - | |
|
| 9.7941 | 95 | 0.0 | 4.5162 | 0.0245 | 0.0268 | 0.0224 | 0.0238 | 0.0224 | |
|
| 8.2353 | 96 | 8.7854 | - | - | - | - | - | - | |
|
| 8.4706 | 97 | 9.0167 | - | - | - | - | - | - | |
|
| 8.7059 | 98 | 9.0405 | - | - | - | - | - | - | |
|
| 8.9412 | 99 | 7.7069 | - | - | - | - | - | - | |
|
| 9.1765 | 100 | 0.6267 | - | - | - | - | - | - | |
|
| 9.4118 | 101 | 0.4043 | - | - | - | - | - | - | |
|
| 9.6471 | 102 | 0.7028 | - | - | - | - | - | - | |
|
| 9.8824 | 103 | 0.751 | - | - | - | - | - | - | |
|
| 10.1176 | 104 | 0.5994 | - | - | - | - | - | - | |
|
| 10.3529 | 105 | 1.0402 | - | - | - | - | - | - | |
|
| 10.5882 | 106 | 0.3983 | 4.4860 | 0.0259 | 0.0301 | 0.0252 | 0.0265 | 0.0252 | |
|
| 9.0294 | 107 | 1.1037 | - | - | - | - | - | - | |
|
| 9.2647 | 108 | 8.6263 | - | - | - | - | - | - | |
|
| 9.5 | 109 | 8.9359 | - | - | - | - | - | - | |
|
| 9.7353 | 110 | 8.9879 | - | - | - | - | - | - | |
|
| 9.9706 | 111 | 6.4932 | - | - | - | - | - | - | |
|
| 10.2059 | 112 | 0.3904 | - | - | - | - | - | - | |
|
| 10.4412 | 113 | 0.3544 | - | - | - | - | - | - | |
|
| 10.6765 | 114 | 0.5658 | - | - | - | - | - | - | |
|
| 10.9118 | 115 | 0.5884 | - | - | - | - | - | - | |
|
| 11.1471 | 116 | 0.4828 | - | - | - | - | - | - | |
|
| 11.3824 | 117 | 0.8872 | - | - | - | - | - | - | |
|
| 11.6176 | 118 | 0.2906 | 4.4899 | 0.0237 | 0.0267 | 0.0264 | 0.0242 | 0.0264 | |
|
| 10.0588 | 119 | 2.1398 | - | - | - | - | - | - | |
|
| 10.2941 | 120 | 8.6036 | - | - | - | - | - | - | |
|
| 10.5294 | 121 | 8.7739 | - | - | - | - | - | - | |
|
| 10.7647 | 122 | 9.1481 | - | - | - | - | - | - | |
|
| 11.0 | 123 | 5.2436 | - | - | - | - | - | - | |
|
| 11.2353 | 124 | 0.2435 | - | - | - | - | - | - | |
|
| 11.4706 | 125 | 0.4451 | - | - | - | - | - | - | |
|
| 11.7059 | 126 | 0.4338 | - | - | - | - | - | - | |
|
| 11.9412 | 127 | 0.5156 | - | - | - | - | - | - | |
|
| 12.1765 | 128 | 0.7081 | - | - | - | - | - | - | |
|
| 12.4118 | 129 | 0.375 | - | - | - | - | - | - | |
|
| **12.6471** | **130** | **0.1906** | **4.5243** | **0.0305** | **0.0253** | **0.0217** | **0.0214** | **0.0217** | |
|
| 11.0882 | 131 | 3.115 | - | - | - | - | - | - | |
|
| 11.3235 | 132 | 8.702 | - | - | - | - | - | - | |
|
| 11.5588 | 133 | 8.4872 | - | - | - | - | - | - | |
|
| 11.7941 | 134 | 9.0143 | - | - | - | - | - | - | |
|
| 12.0294 | 135 | 4.2374 | - | - | - | - | - | - | |
|
| 12.2647 | 136 | 0.1979 | - | - | - | - | - | - | |
|
| 12.5 | 137 | 0.6371 | - | - | - | - | - | - | |
|
| 12.7353 | 138 | 0.5763 | - | - | - | - | - | - | |
|
| 12.9706 | 139 | 0.5716 | - | - | - | - | - | - | |
|
| 13.2059 | 140 | 0.9894 | - | - | - | - | - | - | |
|
| 13.4412 | 141 | 0.3963 | - | - | - | - | - | - | |
|
| 13.6765 | 142 | 0.084 | 4.5514 | 0.0224 | 0.0253 | 0.0209 | 0.0250 | 0.0209 | |
|
| 12.1176 | 143 | 4.1455 | - | - | - | - | - | - | |
|
| 12.3529 | 144 | 8.6664 | - | - | - | - | - | - | |
|
| 12.5882 | 145 | 8.5896 | - | - | - | - | - | - | |
|
| 12.8235 | 146 | 8.9639 | - | - | - | - | - | - | |
|
| 13.0588 | 147 | 3.2692 | - | - | - | - | - | - | |
|
| 13.2941 | 148 | 0.2518 | - | - | - | - | - | - | |
|
| 13.5294 | 149 | 0.8313 | - | - | - | - | - | - | |
|
| 13.7647 | 150 | 0.5592 | - | - | - | - | - | - | |
|
| 14.0 | 151 | 0.3966 | - | - | - | - | - | - | |
|
| 14.2353 | 152 | 0.829 | - | - | - | - | - | - | |
|
| 14.4706 | 153 | 0.2369 | - | - | - | - | - | - | |
|
| 14.7059 | 154 | 0.0629 | 4.5549 | 0.0294 | 0.0312 | 0.0258 | 0.0315 | 0.0258 | |
|
| 13.1471 | 155 | 5.1674 | - | - | - | - | - | - | |
|
| 13.3824 | 156 | 8.5543 | - | - | - | - | - | - | |
|
| 13.6176 | 157 | 8.4481 | - | - | - | - | - | - | |
|
| 13.8529 | 158 | 8.7815 | - | - | - | - | - | - | |
|
| 14.0882 | 159 | 1.9305 | - | - | - | - | - | - | |
|
| 14.3235 | 160 | 0.0925 | - | - | - | - | - | - | |
|
| 14.5588 | 161 | 0.6568 | - | - | - | - | - | - | |
|
| 14.7941 | 162 | 0.2796 | - | - | - | - | - | - | |
|
| 15.0294 | 163 | 0.5503 | - | - | - | - | - | - | |
|
| 15.2647 | 164 | 0.6386 | - | - | - | - | - | - | |
|
| 15.5 | 165 | 0.1957 | - | - | - | - | - | - | |
|
| 15.7353 | 166 | 0.0137 | 4.5688 | 0.0210 | 0.0251 | 0.0251 | 0.0223 | 0.0251 | |
|
| 14.1765 | 167 | 6.2283 | - | - | - | - | - | - | |
|
| 14.4118 | 168 | 8.5378 | - | - | - | - | - | - | |
|
| 14.6471 | 169 | 8.5173 | - | - | - | - | - | - | |
|
| 14.8824 | 170 | 8.9953 | - | - | - | - | - | - | |
|
| 15.1176 | 171 | 0.983 | - | - | - | - | - | - | |
|
| 15.3529 | 172 | 0.1503 | - | - | - | - | - | - | |
|
| 15.5882 | 173 | 0.9004 | - | - | - | - | - | - | |
|
| 15.8235 | 174 | 0.3962 | - | - | - | - | - | - | |
|
| 16.0588 | 175 | 0.4047 | - | - | - | - | - | - | |
|
| 16.2941 | 176 | 0.8265 | - | - | - | - | - | - | |
|
| 16.5294 | 177 | 0.3069 | - | - | - | - | - | - | |
|
| 16.7647 | 178 | 0.0 | 4.5819 | 0.0219 | 0.0271 | 0.0240 | 0.0253 | 0.0240 | |
|
| 15.2059 | 179 | 7.3186 | - | - | - | - | - | - | |
|
| 15.4412 | 180 | 8.5984 | - | - | - | - | - | - | |
|
| 15.6765 | 181 | 8.5362 | - | - | - | - | - | - | |
|
| 15.9118 | 182 | 8.2934 | - | - | - | - | - | - | |
|
| 16.1471 | 183 | 0.437 | - | - | - | - | - | - | |
|
| 16.3824 | 184 | 0.1864 | - | - | - | - | - | - | |
|
| 16.6176 | 185 | 0.2657 | - | - | - | - | - | - | |
|
| 16.8529 | 186 | 0.4242 | - | - | - | - | - | - | |
|
| 17.0882 | 187 | 0.4815 | - | - | - | - | - | - | |
|
| 17.3235 | 188 | 0.5206 | - | - | - | - | - | - | |
|
| 17.5588 | 189 | 0.1981 | - | - | - | - | - | - | |
|
| 17.7941 | 190 | 0.0 | 4.5795 | 0.0249 | 0.0319 | 0.0287 | 0.0227 | 0.0287 | |
|
| 16.2353 | 191 | 8.2837 | - | - | - | - | - | - | |
|
| 16.4706 | 192 | 8.5457 | - | - | - | - | - | - | |
|
| 16.7059 | 193 | 8.6284 | - | - | - | - | - | - | |
|
| 16.9412 | 194 | 7.1806 | - | - | - | - | - | - | |
|
| 17.1765 | 195 | 0.2714 | - | - | - | - | - | - | |
|
| 17.4118 | 196 | 0.65 | - | - | - | - | - | - | |
|
| 17.6471 | 197 | 0.3627 | - | - | - | - | - | - | |
|
| 17.8824 | 198 | 0.2502 | - | - | - | - | - | - | |
|
| 18.1176 | 199 | 0.4651 | - | - | - | - | - | - | |
|
| 18.3529 | 200 | 0.3878 | - | - | - | - | - | - | |
|
| 18.5882 | 201 | 0.1728 | 4.5870 | 0.0258 | 0.0321 | 0.0293 | 0.0290 | 0.0293 | |
|
| 17.0294 | 202 | 1.0158 | - | - | - | - | - | - | |
|
| 17.2647 | 203 | 8.1391 | - | - | - | - | - | - | |
|
| 17.5 | 204 | 8.5323 | - | - | - | - | - | - | |
|
| 17.7353 | 205 | 8.6644 | - | - | - | - | - | - | |
|
| 17.9706 | 206 | 6.1161 | - | - | - | - | - | - | |
|
| 18.2059 | 207 | 0.4636 | - | - | - | - | - | - | |
|
| 18.4412 | 208 | 0.8765 | - | - | - | - | - | - | |
|
| 18.6765 | 209 | 0.4075 | - | - | - | - | - | - | |
|
| 18.9118 | 210 | 0.3211 | - | - | - | - | - | - | |
|
| 19.1471 | 211 | 0.65 | - | - | - | - | - | - | |
|
| 19.3824 | 212 | 0.4802 | - | - | - | - | - | - | |
|
| 19.6176 | 213 | 0.0777 | 4.5921 | 0.0211 | 0.0268 | 0.0238 | 0.0260 | 0.0238 | |
|
| 18.0588 | 214 | 1.9364 | - | - | - | - | - | - | |
|
| 18.2941 | 215 | 8.3079 | - | - | - | - | - | - | |
|
| 18.5294 | 216 | 8.4468 | - | - | - | - | - | - | |
|
| 18.7647 | 217 | 8.8501 | - | - | - | - | - | - | |
|
| 19.0 | 218 | 5.0076 | - | - | - | - | - | - | |
|
| 19.2353 | 219 | 0.1596 | - | - | - | - | - | - | |
|
| 19.4706 | 220 | 0.6482 | - | - | - | - | - | - | |
|
| 19.7059 | 221 | 0.5019 | - | - | - | - | - | - | |
|
| 19.9412 | 222 | 0.2596 | - | - | - | - | - | - | |
|
| 20.1765 | 223 | 0.5857 | - | - | - | - | - | - | |
|
| 20.4118 | 224 | 0.3469 | - | - | - | - | - | - | |
|
| 20.6471 | 225 | 0.082 | 4.5951 | 0.0251 | 0.0293 | 0.0239 | 0.0259 | 0.0239 | |
|
| 19.0882 | 226 | 3.0141 | - | - | - | - | - | - | |
|
| 19.3235 | 227 | 8.3977 | - | - | - | - | - | - | |
|
| 19.5588 | 228 | 8.2687 | - | - | - | - | - | - | |
|
| 19.7941 | 229 | 8.8415 | - | - | - | - | - | - | |
|
| 20.0294 | 230 | 3.9692 | - | - | - | - | - | - | |
|
| 20.2647 | 231 | 0.2079 | - | - | - | - | - | - | |
|
| 20.5 | 232 | 0.6167 | - | - | - | - | - | - | |
|
| 20.7353 | 233 | 0.255 | - | - | - | - | - | - | |
|
| 20.9706 | 234 | 0.2403 | - | - | - | - | - | - | |
|
| 21.2059 | 235 | 0.5944 | - | - | - | - | - | - | |
|
| 21.4412 | 236 | 0.4212 | - | - | - | - | - | - | |
|
| 21.6765 | 237 | 0.1031 | 4.5929 | 0.0248 | 0.0301 | 0.0297 | 0.0268 | 0.0297 | |
|
| 20.1176 | 238 | 4.0698 | - | - | - | - | - | - | |
|
| 20.3529 | 239 | 8.3696 | - | - | - | - | - | - | |
|
| 20.5882 | 240 | 8.2668 | - | - | - | - | - | - | |
|
| 20.8235 | 241 | 8.8194 | - | - | - | - | - | - | |
|
| 21.0588 | 242 | 2.9283 | - | - | - | - | - | - | |
|
| 21.2941 | 243 | 0.0974 | - | - | - | - | - | - | |
|
| 21.5294 | 244 | 0.5172 | - | - | - | - | - | - | |
|
| 21.7647 | 245 | 0.2451 | - | - | - | - | - | - | |
|
| 22.0 | 246 | 0.4693 | - | - | - | - | - | - | |
|
| 22.2353 | 247 | 0.7352 | - | - | - | - | - | - | |
|
| 22.4706 | 248 | 0.1933 | - | - | - | - | - | - | |
|
| 22.7059 | 249 | 0.0552 | 4.5945 | 0.0261 | 0.0275 | 0.0279 | 0.0204 | 0.0279 | |
|
| 21.1471 | 250 | 5.1237 | - | - | - | - | - | - | |
|
| 21.3824 | 251 | 8.5068 | - | - | - | - | - | - | |
|
| 21.6176 | 252 | 8.2828 | - | - | - | - | - | - | |
|
| 21.8529 | 253 | 8.7851 | - | - | - | - | - | - | |
|
| 22.0882 | 254 | 2.0883 | - | - | - | - | - | - | |
|
| 22.3235 | 255 | 0.1147 | - | - | - | - | - | - | |
|
| 22.5588 | 256 | 0.5259 | - | - | - | - | - | - | |
|
| 22.7941 | 257 | 0.2915 | - | - | - | - | - | - | |
|
| 23.0294 | 258 | 0.2495 | - | - | - | - | - | - | |
|
| 23.2647 | 259 | 0.7518 | - | - | - | - | - | - | |
|
| 23.5 | 260 | 0.1767 | - | - | - | - | - | - | |
|
| 23.7353 | 261 | 0.0244 | 4.5944 | 0.0213 | 0.0267 | 0.0265 | 0.0220 | 0.0265 | |
|
| 22.1765 | 262 | 6.1144 | - | - | - | - | - | - | |
|
| 22.4118 | 263 | 8.3334 | - | - | - | - | - | - | |
|
| 22.6471 | 264 | 8.4377 | - | - | - | - | - | - | |
|
| 22.8824 | 265 | 8.8182 | - | - | - | - | - | - | |
|
| 23.1176 | 266 | 0.8795 | - | - | - | - | - | - | |
|
| 23.3529 | 267 | 0.0637 | - | - | - | - | - | - | |
|
| 23.5882 | 268 | 0.3658 | - | - | - | - | - | - | |
|
| 23.8235 | 269 | 0.3599 | - | - | - | - | - | - | |
|
| 24.0588 | 270 | 0.283 | - | - | - | - | - | - | |
|
| 24.2941 | 271 | 0.731 | - | - | - | - | - | - | |
|
| 24.5294 | 272 | 0.1758 | - | - | - | - | - | - | |
|
| 24.7647 | 273 | 0.0 | 4.5963 | 0.0259 | 0.0295 | 0.0247 | 0.0229 | 0.0247 | |
|
| 23.2059 | 274 | 7.1188 | - | - | - | - | - | - | |
|
| 23.4412 | 275 | 8.354 | - | - | - | - | - | - | |
|
| 23.6765 | 276 | 8.5186 | - | - | - | - | - | - | |
|
| 23.9118 | 277 | 8.1633 | - | - | - | - | - | - | |
|
| 24.1471 | 278 | 0.3481 | - | - | - | - | - | - | |
|
| 24.3824 | 279 | 0.574 | - | - | - | - | - | - | |
|
| 24.6176 | 280 | 0.2784 | - | - | - | - | - | - | |
|
| 24.8529 | 281 | 0.251 | - | - | - | - | - | - | |
|
| 25.0882 | 282 | 0.4093 | - | - | - | - | - | - | |
|
| 25.3235 | 283 | 0.5414 | - | - | - | - | - | - | |
|
| 25.5588 | 284 | 0.149 | - | - | - | - | - | - | |
|
| 25.7941 | 285 | 0.0 | 4.5965 | 0.0223 | 0.0251 | 0.0240 | 0.0204 | 0.0240 | |
|
| 24.2353 | 286 | 8.2498 | - | - | - | - | - | - | |
|
| 24.4706 | 287 | 8.4555 | - | - | - | - | - | - | |
|
| 24.7059 | 288 | 8.5368 | - | - | - | - | - | - | |
|
| 24.9412 | 289 | 7.1779 | - | - | - | - | - | - | |
|
| 25.1765 | 290 | 0.1486 | - | - | - | - | - | - | |
|
| 25.4118 | 291 | 0.9156 | - | - | - | - | - | - | |
|
| 25.6471 | 292 | 0.2757 | - | - | - | - | - | - | |
|
| 25.8824 | 293 | 0.237 | - | - | - | - | - | - | |
|
| 26.1176 | 294 | 0.2979 | - | - | - | - | - | - | |
|
| 26.3529 | 295 | 0.5296 | - | - | - | - | - | - | |
|
| 26.5882 | 296 | 0.2062 | 4.5949 | 0.0259 | 0.0327 | 0.0308 | 0.0247 | 0.0308 | |
|
| 25.0294 | 297 | 1.0355 | - | - | - | - | - | - | |
|
| 25.2647 | 298 | 8.1721 | - | - | - | - | - | - | |
|
| 25.5 | 299 | 8.4028 | - | - | - | - | - | - | |
|
| 25.7353 | 300 | 8.5989 | 4.5941 | 0.0260 | 0.0262 | 0.0243 | 0.0226 | 0.0243 | |
|
|
|
* The bold row denotes the saved checkpoint. |
|
</details> |
|
|
|
### Framework Versions |
|
- Python: 3.10.12 |
|
- Sentence Transformers: 3.0.1 |
|
- Transformers: 4.41.2 |
|
- PyTorch: 2.1.2+cu121 |
|
- Accelerate: 0.32.0 |
|
- 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.* |
|
--> |
