N_roberta_sst5_padding40model – AI Model by Realgon | AlphaNeural AI

You can deploy this model and start earning money today!

Realgon/
N_roberta_sst5_padding40model

like

0

text-classification

generated_from_trainer

FacebookAI/roberta-base

autotrain_compatible

endpoints_compatible

Views

No views yet

N_roberta_sst5_padding40model

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

Loss: 3.6174
Accuracy: 0.5552

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: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.3242	1.0	534	1.1718	0.4973
1.021	2.0	1068	1.0277	0.5643
0.8685	3.0	1602	1.0361	0.5588
0.7377	4.0	2136	1.1282	0.5602
0.5968	5.0	2670	1.2513	0.5597
0.4867	6.0	3204	1.4148	0.5611
0.3856	7.0	3738	1.5733	0.5489
0.305	8.0	4272	1.7751	0.5443
0.2631	9.0	4806	1.9540	0.5498
0.223	10.0	5340	2.2826	0.5326
0.1976	11.0	5874	2.3130	0.5548
0.1666	12.0	6408	2.6703	0.5611
0.144	13.0	6942	3.0894	0.5557
0.1196	14.0	7476	3.1486	0.5557
0.1016	15.0	8010	3.3404	0.5516
0.0653	16.0	8544	3.4713	0.5421
0.0691	17.0	9078	3.5334	0.5507
0.0483	18.0	9612	3.5719	0.5534
0.0438	19.0	10146	3.6175	0.5543
0.0439	20.0	10680	3.6174	0.5552

Framework versions

Transformers 4.33.2
Pytorch 2.0.1+cu117
Datasets 2.14.5
Tokenizers 0.13.3