XLMR-ENIS-finetuned-stsb

vesteinn/XLMR-ENIS-finetuned-stsb

XLMR-ENIS-finetuned-stsb is a sentence similarity model from vesteinn. Use it when you need a score for how close two texts are. It is set up for transformers. The card lists the license as agpl-3.0.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

4% of all-time downloads

All-time downloads

Public

Parameters

124M

1.5 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin498 MB · 50%

Parameter types

How the weights are stored.

F32124M · 100%

Base models

vesteinn/XLMR-ENIS

Datasets

nyu-mll/glue

Model card

From the Hugging Face model README

XLMR-ENIS-finetuned-stsb

This model is a fine-tuned version of vesteinn/XLMR-ENIS on the glue dataset. It achieves the following results on the evaluation set:

Loss: 0.5232
Pearson: 0.8915
Spearmanr: 0.8888

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 2e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Pearson	Spearmanr
No log	1.0	360	0.6330	0.8562	0.8570
1.2835	2.0	720	0.6368	0.8790	0.8781
0.4518	3.0	1080	0.5352	0.8883	0.8852
0.4518	4.0	1440	0.4881	0.8910	0.8885
0.288	5.0	1800	0.5232	0.8915	0.8888

Framework versions

Transformers 4.11.3
Pytorch 1.9.0+cu111
Datasets 1.13.0
Tokenizers 0.10.3

Task: Sentence Similarity
Library: transformers
Type: xlm-roberta
License: agpl-3.0
Created: Mar 2, 2022
Updated: Feb 25, 2025