xlm-roberta-base-fake-news-german – AI Model by krisschaaf | AlphaNeural AI

You can deploy this model and start earning money today!

krisschaaf/
xlm-roberta-base-fake-news-german

like

0

text-classification

generated_from_trainer

FacebookAI/xlm-roberta-base

autotrain_compatible

endpoints_compatible

Views

No views yet

trainer_output

This model is a fine-tuned version of FacebookAI/xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.1527
Accuracy: 0.9717
F1: 0.9716
Precision: 0.9716
Recall: 0.9717

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: 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
lr_scheduler_warmup_steps: 573
num_epochs: 5
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
0.1714	1.0	1147	0.1891	0.9302	0.9308	0.9350	0.9302
0.105	2.0	2294	0.1224	0.9627	0.9625	0.9633	0.9627
0.0689	3.0	3441	0.1218	0.9695	0.9693	0.9698	0.9695
0.0341	4.0	4588	0.1358	0.9714	0.9714	0.9715	0.9714
0.0228	5.0	5735	0.1429	0.9730	0.9729	0.9730	0.9730

Framework versions

Transformers 4.52.4
Pytorch 2.6.0+cu124
Datasets 2.14.4
Tokenizers 0.21.1