|
--- |
|
pipeline_tag: sentence-similarity |
|
tags: |
|
- sentence-transformers |
|
- feature-extraction |
|
- sentence-similarity |
|
--- |
|
|
|
# SGPT-1.3B-weightedmean-nli-bitfit |
|
|
|
## Usage |
|
|
|
For usage instructions, refer to our codebase: https://github.com/Muennighoff/sgpt |
|
|
|
## Evaluation Results |
|
|
|
For eval results, refer to the eval folder or our paper: https://arxiv.org/abs/2202.08904 |
|
|
|
## Training |
|
The model was trained with the parameters: |
|
|
|
**DataLoader**: |
|
|
|
`sentence_transformers.datasets.NoDuplicatesDataLoader.NoDuplicatesDataLoader` of length 93941 with parameters: |
|
``` |
|
{'batch_size': 6} |
|
``` |
|
|
|
**Loss**: |
|
|
|
`sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss` with parameters: |
|
``` |
|
{'scale': 20.0, 'similarity_fct': 'cos_sim'} |
|
``` |
|
|
|
Parameters of the fit()-Method: |
|
``` |
|
{ |
|
"epochs": 1, |
|
"evaluation_steps": 9394, |
|
"evaluator": "sentence_transformers.evaluation.EmbeddingSimilarityEvaluator.EmbeddingSimilarityEvaluator", |
|
"max_grad_norm": 1, |
|
"optimizer_class": "<class 'transformers.optimization.AdamW'>", |
|
"optimizer_params": { |
|
"lr": 0.0001 |
|
}, |
|
"scheduler": "WarmupLinear", |
|
"steps_per_epoch": null, |
|
"warmup_steps": 9395, |
|
"weight_decay": 0.01 |
|
} |
|
``` |
|
|
|
|
|
## Full Model Architecture |
|
``` |
|
SentenceTransformer( |
|
(0): Transformer({'max_seq_length': 75, 'do_lower_case': False}) with Transformer model: GPTNeoModel |
|
(1): Pooling({'word_embedding_dimension': 2048, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': True, 'pooling_mode_lasttoken': False}) |
|
) |
|
``` |
|
|
|
## Citing & Authors |
|
|
|
```bibtex |
|
@article{muennighoff2022sgpt, |
|
title={SGPT: GPT Sentence Embeddings for Semantic Search}, |
|
author={Muennighoff, Niklas}, |
|
journal={arXiv preprint arXiv:2202.08904}, |
|
year={2022} |
|
} |
|
``` |
|
|
