arabert_baseline_development_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: 0.8217
• Qwk: -0.0645
• Mse: 0.7668

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	3.8893	-0.0248	3.7493
No log	1.3333	4	1.6163	-0.1603	1.5205
No log	2.0	6	1.3910	-0.0522	1.3168
No log	2.6667	8	0.9920	-0.1846	0.9528
No log	3.3333	10	0.9604	-0.5098	0.9287
No log	4.0	12	0.7779	-0.1308	0.7306
No log	4.6667	14	0.7914	0.0	0.7387
No log	5.3333	16	0.8497	0.0	0.7909
No log	6.0	18	0.8019	0.0351	0.7466
No log	6.6667	20	0.7900	0.0748	0.7369
No log	7.3333	22	0.7934	-0.0645	0.7422
No log	8.0	24	0.8050	-0.0645	0.7531
No log	8.6667	26	0.8063	-0.0645	0.7543
No log	9.3333	28	0.8142	-0.0645	0.7607
No log	10.0	30	0.8217	-0.0645	0.7668

Framework versions

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