Modelpublic

versae/fineweb-edu-scorer-norwegian

sourceHugging Faceapache-2.0updated 1y agoView on Hugging Face

0likes6downloads

Model Card

fineweb-edu-scorer-norwegian

This model is a fine-tuned version of Snowflake/snowflake-arctic-embed-m on an unknown dataset. It achieves the following results on the evaluation set:

—Loss: 0.8676
—Precision: 0.3781
—Recall: 0.3090
—F1 Macro: 0.2956
—Accuracy: 0.4576

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: 0.0003
—trainbatchsize: 256
—evalbatchsize: 128
—seed: 0
—optimizer: Use OptimizerNames.ADAMWTORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
—lrschedulertype: linear
—num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1 Macro	Accuracy
No log	0	0	3.5740	0.0587	0.1667	0.0869	0.3524
0.9284	2.6882	1000	0.9383	0.3586	0.2876	0.2661	0.415
0.9173	5.3763	2000	0.9238	0.3442	0.2939	0.2736	0.4392
0.9011	8.0645	3000	0.9369	0.3620	0.2941	0.2793	0.3936
0.8666	10.7527	4000	0.8862	0.3692	0.2987	0.2832	0.44
0.8595	13.4409	5000	0.8799	0.3647	0.3018	0.2883	0.4314
0.8474	16.1290	6000	0.8703	0.3773	0.3097	0.2983	0.4456
0.8488	18.8172	7000	0.8676	0.3781	0.3090	0.2956	0.4576

Framework versions

—Transformers 4.53.2
—Pytorch 2.7.1+cu126
—Datasets 4.0.0
—Tokenizers 0.21.2