arabert_baseline_vocabulary_task8_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: 0.3519
• Qwk: 0.7059
• Mse: 0.3519

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	0.5	2	2.4116	0.0	2.4116
No log	1.0	4	1.3953	0.1860	1.3953
No log	1.5	6	0.6553	0.5772	0.6553
No log	2.0	8	0.5969	0.5977	0.5969
No log	2.5	10	0.4486	0.7059	0.4486
No log	3.0	12	0.2418	0.8011	0.2418
No log	3.5	14	0.3669	0.7059	0.3669
No log	4.0	16	0.7921	0.5459	0.7921
No log	4.5	18	0.5441	0.6277	0.5441
No log	5.0	20	0.3384	0.7168	0.3384
No log	5.5	22	0.3399	0.7572	0.3399
No log	6.0	24	0.3927	0.6939	0.3927
No log	6.5	26	0.5647	0.6277	0.5647
No log	7.0	28	0.5237	0.6356	0.5237
No log	7.5	30	0.3655	0.7794	0.3655
No log	8.0	32	0.2983	0.7794	0.2983
No log	8.5	34	0.3016	0.7794	0.3016
No log	9.0	36	0.3254	0.7794	0.3254
No log	9.5	38	0.3414	0.7667	0.3414
No log	10.0	40	0.3519	0.7059	0.3519

Framework versions

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