xlm-roberta-base-FakeNews-Dravidian-final – AI Model by mdosama39 | AlphaNeural AI

You can deploy this model and start earning money today!

mdosama39/
xlm-roberta-base-FakeNews-Dravidian-final

like

0

text-classification

generated_from_trainer

FacebookAI/xlm-roberta-base

autotrain_compatible

endpoints_compatible

Views

No views yet

xlm-roberta-base-FakeNews-Dravidian-final

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

Loss: 0.0156
Accuracy: 0.9975
Weighted f1 score: 0.9975
Macro f1 score: 0.9975

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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Weighted f1 score	Macro f1 score
0.5564	1.0	255	0.3382	0.8491	0.8467	0.8467
0.3623	2.0	510	0.1918	0.9374	0.9374	0.9373
0.2767	3.0	765	0.1356	0.9509	0.9509	0.9509
0.2274	4.0	1020	0.1168	0.9632	0.9632	0.9631
0.1727	5.0	1275	0.0740	0.9865	0.9865	0.9865
0.1296	6.0	1530	0.0819	0.9816	0.9816	0.9816
0.1278	7.0	1785	0.0310	0.9951	0.9951	0.9951
0.0904	8.0	2040	0.0248	0.9951	0.9951	0.9951
0.0548	9.0	2295	0.0198	0.9975	0.9975	0.9975
0.0545	10.0	2550	0.0156	0.9975	0.9975	0.9975

Framework versions

Transformers 4.35.0
Pytorch 2.0.0
Datasets 2.11.0
Tokenizers 0.14.1