Modelpublic

SADAF-IMAMU/train

sourceHugging Faceupdated 3y agoView on Hugging Face

0likes26downloads

Model Card

train

This model is a fine-tuned version of aubmindlab/bert-base-arabertv02 on an unknown dataset. It achieves the following results on the evaluation set:

—Loss: 0.9948
—Macro F1: 0.7856
—Precision: 0.7820
—Recall: 0.7956
—Kappa: 0.6940
—Accuracy: 0.7956

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
—trainbatchsize: 16
—evalbatchsize: 128
—seed: 25
—gradientaccumulationsteps: 2
—totaltrainbatch_size: 32
—optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
—lrschedulertype: linear
—num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Macro F1	Precision	Recall	Kappa	Accuracy
No log	1.0	101	1.1562	0.6031	0.5561	0.7044	0.4967	0.7044
No log	2.0	203	0.9119	0.7151	0.7107	0.7672	0.6236	0.7672
No log	3.0	304	0.8493	0.7280	0.7139	0.7734	0.6381	0.7734
No log	4.0	406	0.8087	0.7455	0.7632	0.7648	0.6421	0.7648
0.9431	5.0	507	0.7735	0.7779	0.7741	0.7931	0.6858	0.7931
0.9431	6.0	609	0.8201	0.7753	0.7735	0.7869	0.6797	0.7869
0.9431	7.0	710	0.8564	0.7886	0.7883	0.8017	0.7004	0.8017
0.9431	8.0	812	0.8712	0.7799	0.7754	0.7894	0.6854	0.7894
0.9431	9.0	913	0.9142	0.7775	0.7751	0.7869	0.6811	0.7869
0.2851	10.0	1015	0.9007	0.7820	0.7764	0.7943	0.6913	0.7943
0.2851	11.0	1116	0.9425	0.7859	0.7825	0.7956	0.6940	0.7956
0.2851	12.0	1218	0.9798	0.7815	0.7797	0.7906	0.6869	0.7906
0.2851	13.0	1319	0.9895	0.7895	0.7860	0.7993	0.7003	0.7993
0.2851	14.0	1421	0.9872	0.7854	0.7813	0.7943	0.6935	0.7943
0.1273	14.93	1515	0.9948	0.7856	0.7820	0.7956	0.6940	0.7956

Framework versions

—Transformers 4.30.2
—Pytorch 2.0.1+cu118
—Tokenizers 0.13.3