N_roberta_agnews_padding40model – AI Model by Realgon | AlphaNeural AI

You can deploy this model and start earning money today!

Realgon/
N_roberta_agnews_padding40model

like

0

text-classification

generated_from_trainer

FacebookAI/roberta-base

autotrain_compatible

endpoints_compatible

Views

No views yet

N_roberta_agnews_padding40model

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

Loss: 0.5563
Accuracy: 0.95

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
0.1981	1.0	7500	0.2012	0.9413
0.1726	2.0	15000	0.2037	0.9457
0.1511	3.0	22500	0.2177	0.9434
0.1242	4.0	30000	0.2438	0.9480
0.0986	5.0	37500	0.2483	0.9482
0.0803	6.0	45000	0.2855	0.9495
0.0733	7.0	52500	0.3275	0.9454
0.0505	8.0	60000	0.3980	0.9441
0.0404	9.0	67500	0.3872	0.9480
0.0277	10.0	75000	0.4156	0.9470
0.0261	11.0	82500	0.4207	0.9483
0.0221	12.0	90000	0.4508	0.9457
0.0224	13.0	97500	0.4591	0.9475
0.0095	14.0	105000	0.4958	0.9466
0.0085	15.0	112500	0.5201	0.9479
0.0064	16.0	120000	0.5334	0.9470
0.0065	17.0	127500	0.5012	0.9488
0.008	18.0	135000	0.5167	0.9492
0.0033	19.0	142500	0.5535	0.9493
0.0024	20.0	150000	0.5563	0.95

Framework versions

Transformers 4.33.2
Pytorch 2.0.1+cu117
Datasets 2.14.5
Tokenizers 0.13.3