roberta-base_ag_news – AI Model by nicolasacosta | AlphaNeural AI

You can deploy this model and start earning money today!

nicolasacosta/
roberta-base_ag_news

like

0

generated_from_trainer

FacebookAI/roberta-base

Views

No views yet

roberta-base_ag_news

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

Loss: 0.1847
Accuracy: 0.9471
F1: 0.9472
Precision: 0.9477
Recall: 0.9471

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: 5e-05
train_batch_size: 8
eval_batch_size: 8
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
lr_scheduler_warmup_steps: 500
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
0.092	1.0	15000	0.2003	0.9408	0.9408	0.9414	0.9408
0.1153	2.0	30000	0.1847	0.9471	0.9472	0.9477	0.9471
0.1538	3.0	45000	0.1855	0.9471	0.9472	0.9479	0.9471
0.143	4.0	60000	0.1887	0.9526	0.9527	0.9530	0.9526
0.0561	5.0	75000	0.1896	0.9518	0.9519	0.9521	0.9518

Framework versions

PEFT 0.14.0
Transformers 4.51.1
Pytorch 2.5.1+cu124
Datasets 3.5.0
Tokenizers 0.21.0