Views
No views yet
sentence_transformers.datasets.NoDuplicatesDataLoader.NoDuplicatesDataLoader of length 8807 with parameters:{'batch_size': 64}sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss with parameters:{'scale': 20.0, 'similarity_fct': 'cos_sim'}{
"epochs": 1,
"evaluation_steps": 880,
"evaluator": "sentence_transformers.evaluation.EmbeddingSimilarityEvaluator.EmbeddingSimilarityEvaluator",
"max_grad_norm": 1,
"optimizer_class": "<class 'transformers.optimization.AdamW'>",
"optimizer_params": {
"lr": 2e-05
},
"scheduler": "WarmupLinear",
"steps_per_epoch": null,
"warmup_steps": 881,
"weight_decay": 0.01
}SentenceTransformer(
(0): Transformer({'max_seq_length': 75, 'do_lower_case': False}) with Transformer model: GPTNeoModel
(1): WeightedMeanPooling()
)1@article{muennighoff2022sgpt,
2 title={SGPT: GPT Sentence Embeddings for Semantic Search},
3 author={Muennighoff, Niklas},
4 journal={arXiv preprint arXiv:2202.08904},
5 year={2022}
6}