Modelpublic

AnonymousCS/populism_classifier_bsample_212

sourceHugging Facemitupdated 1y agoView on Hugging Face

0likes9downloads

Model Card

populismclassifierbsample_212

This model is a fine-tuned version of AnonymousCS/populism_xlmr_large on the None dataset. It achieves the following results on the evaluation set:

—Loss: 0.2752
—Accuracy: 0.9801
—1-f1: 0.0
—1-recall: 0.0
—1-precision: 0.0
—Balanced Acc: 0.5

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: 1e-06
—trainbatchsize: 16
—evalbatchsize: 16
—seed: 42
—optimizer: Use adamwtorch with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
—lrschedulertype: linear
—lrschedulerwarmup_ratio: 0.06
—num_epochs: 15
—mixedprecisiontraining: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Balanced Acc
0.6258	1.0	29	0.3913	0.9801	0.5
0.6476	2.0	58	0.3397	0.9801	0.5
0.5355	3.0	87	0.3180	0.9801	0.5
0.6818	4.0	116	0.3074	0.9801	0.5
0.4494	5.0	145	0.2971	0.9801	0.5
0.652	6.0	174	0.2886	0.9801	0.5
0.8645	7.0	203	0.2775	0.9801	0.5
0.7489	8.0	232	0.2806	0.9801	0.5
0.5238	9.0	261	0.2815	0.9801	0.5
0.5113	10.0	290	0.2797	0.9801	0.5
0.5769	11.0	319	0.2755	0.9801	0.5
0.592	12.0	348	0.2747	0.9801	0.5
0.513	13.0	377	0.2757	0.9801	0.5
0.4696	14.0	406	0.2750	0.9801	0.5
0.5106	15.0	435	0.2752	0.9801	0.5

Framework versions

—Transformers 4.46.3
—Pytorch 2.4.1+cu121
—Datasets 3.1.0
—Tokenizers 0.20.3