SloBertAA_Top5_WithOOC_082023 – AI Model by gregorgabrovsek | AlphaNeural AI

You can deploy this model and start earning money today!

gregorgabrovsek/
SloBertAA_Top5_WithOOC_082023

like

0

text-classification

generated_from_trainer

autotrain_compatible

endpoints_compatible

Views

No views yet

SloBertAA_Top5_WithOOC_082023

This model is a fine-tuned version of EMBEDDIA/sloberta on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.7870
Accuracy: 0.9013
F1: 0.9010
Precision: 0.9013
Recall: 0.9013

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: 12
eval_batch_size: 12
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	F1	Precision	Recall
0.381	1.0	10508	0.3981	0.8665	0.8636	0.8666	0.8665
0.2912	2.0	21016	0.3497	0.8855	0.8854	0.8868	0.8855
0.2352	3.0	31524	0.3778	0.8906	0.8901	0.8908	0.8906
0.1875	4.0	42032	0.4656	0.8903	0.8902	0.8920	0.8903
0.1447	5.0	52540	0.5620	0.8944	0.8949	0.8969	0.8944
0.0938	6.0	63048	0.6150	0.8975	0.8975	0.8980	0.8975
0.0685	7.0	73556	0.7084	0.8950	0.8945	0.8953	0.8950
0.0449	8.0	84064	0.7499	0.8997	0.8992	0.8995	0.8997
0.0267	9.0	94572	0.7734	0.8987	0.8983	0.8990	0.8987
0.021	10.0	105080	0.7870	0.9013	0.9010	0.9013	0.9013

Framework versions

Transformers 4.26.1
Pytorch 1.8.0
Datasets 2.10.1
Tokenizers 0.13.2