arabert_baseline_organization_task3_fold0

This model is a fine-tuned version of aubmindlab/bert-base-arabertv02 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.9015
• Qwk: -0.0421
• Mse: 0.8705

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	Qwk	Mse
No log	0.6667	2	4.9483	-0.0614	4.8034
No log	1.3333	4	2.2914	-0.2094	2.1960
No log	2.0	6	1.8214	-0.0434	1.7728
No log	2.6667	8	1.1417	-0.2754	1.1089
No log	3.3333	10	1.0866	-0.1786	1.0561
No log	4.0	12	0.9760	0.0320	0.9412
No log	4.6667	14	0.9213	-0.1786	0.8945
No log	5.3333	16	0.9094	-0.1579	0.8796
No log	6.0	18	0.9277	-0.1048	0.8935
No log	6.6667	20	0.9357	-0.1048	0.9005
No log	7.3333	22	0.9464	-0.1048	0.9094
No log	8.0	24	0.9330	-0.1048	0.8977
No log	8.6667	26	0.9159	-0.1048	0.8827
No log	9.3333	28	0.9041	-0.0421	0.8723
No log	10.0	30	0.9015	-0.0421	0.8705

Framework versions

• Transformers 4.44.0
• Pytorch 2.4.0
• Datasets 2.21.0
• Tokenizers 0.19.1