73 lines
1.8 KiB
Markdown
73 lines
1.8 KiB
Markdown
---
|
|
pipeline_tag: sentence-similarity
|
|
tags:
|
|
- sentence-transformers
|
|
- feature-extraction
|
|
- sentence-similarity
|
|
---
|
|
|
|
# SGPT-125M-lasttoken-msmarco-specb
|
|
|
|
## Usage
|
|
|
|
For usage instructions, refer to our codebase: https://github.com/Muennighoff/sgpt
|
|
|
|
## Evaluation Results
|
|
|
|
For eval results, refer to our paper: https://arxiv.org/abs/2202.08904
|
|
|
|
## Training
|
|
The model was trained with the parameters:
|
|
|
|
**DataLoader**:
|
|
|
|
`torch.utils.data.dataloader.DataLoader` of length 15600 with parameters:
|
|
```
|
|
{'batch_size': 32, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
|
|
```
|
|
|
|
**Loss**:
|
|
|
|
`sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss` with parameters:
|
|
```
|
|
{'scale': 20.0, 'similarity_fct': 'cos_sim'}
|
|
```
|
|
|
|
Parameters of the fit()-Method:
|
|
```
|
|
{
|
|
"epochs": 10,
|
|
"evaluation_steps": 0,
|
|
"evaluator": "NoneType",
|
|
"max_grad_norm": 1,
|
|
"optimizer_class": "<class 'transformers.optimization.AdamW'>",
|
|
"optimizer_params": {
|
|
"lr": 2e-05
|
|
},
|
|
"scheduler": "WarmupLinear",
|
|
"steps_per_epoch": null,
|
|
"warmup_steps": 1000,
|
|
"weight_decay": 0.01
|
|
}
|
|
```
|
|
|
|
|
|
## Full Model Architecture
|
|
```
|
|
SentenceTransformer(
|
|
(0): Transformer({'max_seq_length': 300, 'do_lower_case': False}) with Transformer model: GPTNeoModel
|
|
(1): Pooling({'word_embedding_dimension': 768, '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': False, 'pooling_mode_lasttoken': True})
|
|
)
|
|
```
|
|
|
|
## Citing & Authors
|
|
|
|
```bibtex
|
|
@article{muennighoff2022sgpt,
|
|
title={SGPT: GPT Sentence Embeddings for Semantic Search},
|
|
author={Muennighoff, Niklas},
|
|
journal={arXiv preprint arXiv:2202.08904},
|
|
year={2022}
|
|
}
|
|
```
|