SST-2-GLoRA-p50-seed63

ekiprop/SST-2-GLoRA-p50-seed63

SST-2-GLoRA-p50-seed63 is a machine learning model from ekiprop. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as mit.

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

Downloads · 30 days

25% of all-time downloads

All-time downloads

Public

Repo size

61.9 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors5.6 MB · 54%

At a glance

Library: peft
License: mit
Access: Public
Created: Aug 6, 2025
Updated: Aug 6, 2025
SHA: 4979bbe6

Base models

Model card

From the Hugging Face model README

SST-2-GLoRA-p50-seed63

This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.1851
Accuracy: 0.9427

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: 0.0003
train_batch_size: 32
eval_batch_size: 32
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.3739	0.0950	200	0.2208	0.9209
0.2878	0.1900	400	0.1951	0.9358
0.2691	0.2850	600	0.2008	0.9300
0.2386	0.3800	800	0.1748	0.9346
0.2284	0.4751	1000	0.2433	0.9186
0.2184	0.5701	1200	0.2108	0.9323
0.2204	0.6651	1400	0.1864	0.9346
0.2133	0.7601	1600	0.1851	0.9427
0.2125	0.8551	1800	0.1807	0.9392
0.1994	0.9501	2000	0.1834	0.9381

Framework versions

PEFT 0.16.0
Transformers 4.54.1
Pytorch 2.5.1+cu121
Datasets 4.0.0
Tokenizers 0.21.4

Library: peft
License: mit
Created: Aug 6, 2025
Updated: Aug 6, 2025