arabert_baseline_mechanics_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: 0.4456
• Qwk: 0.7094
• Mse: 0.4456

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	1.7489	0.0491	1.7489
No log	1.0	4	1.3896	0.1642	1.3896
No log	1.5	6	1.1796	0.3277	1.1796
No log	2.0	8	0.9747	0.4703	0.9747
No log	2.5	10	0.8441	0.4560	0.8441
No log	3.0	12	0.7876	0.4560	0.7876
No log	3.5	14	0.7251	0.5758	0.7251
No log	4.0	16	0.6598	0.5919	0.6598
No log	4.5	18	0.6220	0.5919	0.6220
No log	5.0	20	0.5659	0.6571	0.5659
No log	5.5	22	0.5619	0.5709	0.5619
No log	6.0	24	0.5885	0.5056	0.5885
No log	6.5	26	0.5705	0.5056	0.5705
No log	7.0	28	0.5149	0.7094	0.5149
No log	7.5	30	0.4887	0.7094	0.4887
No log	8.0	32	0.4700	0.7094	0.4700
No log	8.5	34	0.4603	0.7094	0.4603
No log	9.0	36	0.4527	0.7094	0.4527
No log	9.5	38	0.4477	0.7821	0.4477
No log	10.0	40	0.4456	0.7094	0.4456

Framework versions

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