{MODEL_NAME}
This is a sentence-transformers model: It maps sentences & paragraphs to a 1024 dimensional dense vector space and can be used for tasks like clustering or semantic search.
Usage (Sentence-Transformers)
Using this model becomes easy when you have sentence-transformers installed:
pip install -U sentence-transformers
Then you can use the model like this:
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('{MODEL_NAME}')
embeddings = model.encode(sentences)
print(embeddings)
Evaluation Results
For an automated evaluation of this model, see the Sentence Embeddings Benchmark: https://seb.sbert.net
Training
The model was trained with the parameters:
DataLoader:
torch.utils.data.dataloader.DataLoader
of length 1196 with parameters:
{'batch_size': 10, 'sampler': 'torch.utils.data.sampler.SequentialSampler', '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": 5,
"evaluation_steps": 50,
"evaluator": "sentence_transformers.evaluation.InformationRetrievalEvaluator.InformationRetrievalEvaluator",
"max_grad_norm": 1,
"optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
"optimizer_params": {
"lr": 2e-05
},
"scheduler": "WarmupLinear",
"steps_per_epoch": null,
"warmup_steps": 598,
"weight_decay": 0.01
}
Full Model Architecture
SentenceTransformer(
(0): Transformer({'max_seq_length': 512, 'do_lower_case': True}) with Transformer model: BertModel
(1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
(2): Normalize()
)
Citing & Authors
- Downloads last month
- 8,733
Spaces using jamesgpt1/sf_model_e5 3
Evaluation results
- accuracy on MTEB AmazonCounterfactualClassification (en)test set self-reported70.851
- ap on MTEB AmazonCounterfactualClassification (en)test set self-reported33.779
- f1 on MTEB AmazonCounterfactualClassification (en)test set self-reported64.970
- accuracy on MTEB AmazonPolarityClassificationtest set self-reported91.809
- ap on MTEB AmazonPolarityClassificationtest set self-reported88.230
- f1 on MTEB AmazonPolarityClassificationtest set self-reported91.786
- accuracy on MTEB AmazonReviewsClassification (en)test set self-reported48.942
- f1 on MTEB AmazonReviewsClassification (en)test set self-reported47.912
- map_at_1 on MTEB ArguAnatest set self-reported39.616
- map_at_10 on MTEB ArguAnatest set self-reported55.938
- map_at_100 on MTEB ArguAnatest set self-reported56.552
- map_at_1000 on MTEB ArguAnatest set self-reported56.556
- map_at_3 on MTEB ArguAnatest set self-reported51.754
- map_at_5 on MTEB ArguAnatest set self-reported54.624
- mrr_at_1 on MTEB ArguAnatest set self-reported40.967
- mrr_at_10 on MTEB ArguAnatest set self-reported56.453
- mrr_at_100 on MTEB ArguAnatest set self-reported57.053
- mrr_at_1000 on MTEB ArguAnatest set self-reported57.057
- mrr_at_3 on MTEB ArguAnatest set self-reported52.312
- mrr_at_5 on MTEB ArguAnatest set self-reported55.100
- ndcg_at_1 on MTEB ArguAnatest set self-reported39.616
- ndcg_at_10 on MTEB ArguAnatest set self-reported64.067
- ndcg_at_100 on MTEB ArguAnatest set self-reported66.384
- ndcg_at_1000 on MTEB ArguAnatest set self-reported66.468
- ndcg_at_3 on MTEB ArguAnatest set self-reported55.740
- ndcg_at_5 on MTEB ArguAnatest set self-reported60.889
- precision_at_1 on MTEB ArguAnatest set self-reported39.616
- precision_at_10 on MTEB ArguAnatest set self-reported8.954
- precision_at_100 on MTEB ArguAnatest set self-reported0.990
- precision_at_1000 on MTEB ArguAnatest set self-reported0.100
- precision_at_3 on MTEB ArguAnatest set self-reported22.428
- precision_at_5 on MTEB ArguAnatest set self-reported15.946
- recall_at_1 on MTEB ArguAnatest set self-reported39.616
- recall_at_10 on MTEB ArguAnatest set self-reported89.545
- recall_at_100 on MTEB ArguAnatest set self-reported99.004
- recall_at_1000 on MTEB ArguAnatest set self-reported99.644
- recall_at_3 on MTEB ArguAnatest set self-reported67.283
- recall_at_5 on MTEB ArguAnatest set self-reported79.730
- v_measure on MTEB ArxivClusteringP2Ptest set self-reported48.729
- v_measure on MTEB ArxivClusteringS2Stest set self-reported42.874
- map on MTEB AskUbuntuDupQuestionstest set self-reported64.321
- mrr on MTEB AskUbuntuDupQuestionstest set self-reported77.879
- cos_sim_pearson on MTEB BIOSSEStest set self-reported88.824
- cos_sim_spearman on MTEB BIOSSEStest set self-reported86.745
- euclidean_pearson on MTEB BIOSSEStest set self-reported86.588
- euclidean_spearman on MTEB BIOSSEStest set self-reported86.745
- manhattan_pearson on MTEB BIOSSEStest set self-reported86.240
- manhattan_spearman on MTEB BIOSSEStest set self-reported86.415
- accuracy on MTEB Banking77Classificationtest set self-reported84.614
- f1 on MTEB Banking77Classificationtest set self-reported83.984
- v_measure on MTEB BiorxivClusteringP2Ptest set self-reported39.731