SST-2-FULL_FT-seed54 – AI Model by ekiprop | AlphaNeural AI

You can deploy this model and start earning money today!

ekiprop/
SST-2-FULL_FT-seed54

like

0

text-classification

generated_from_trainer

FacebookAI/roberta-base

autotrain_compatible

endpoints_compatible

Views

No views yet

SST-2-FULL_FT-seed54

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

Loss: 0.1707
Accuracy: 0.9484

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: 3e-05
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
0.3775	0.0950	200	0.2434	0.9002
0.2933	0.1900	400	0.2036	0.9300
0.2686	0.2850	600	0.2099	0.9220
0.2333	0.3800	800	0.1805	0.9335
0.2146	0.4751	1000	0.3107	0.8933
0.1945	0.5701	1200	0.2015	0.9392
0.1948	0.6651	1400	0.1802	0.9450
0.1894	0.7601	1600	0.1832	0.9438
0.1858	0.8551	1800	0.1707	0.9484
0.1647	0.9501	2000	0.1831	0.9484

Framework versions

Transformers 4.54.1
Pytorch 2.5.1+cu121
Datasets 4.0.0
Tokenizers 0.21.4