arabert_baseline_organization_task3_fold1

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: 0.5660
• Qwk: 0.0120
• Mse: 0.6114

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	3.6631	0.0494	3.6515
No log	1.3333	4	1.3687	-0.0302	1.4053
No log	2.0	6	1.0057	-0.0097	1.0728
No log	2.6667	8	0.5822	0.0403	0.6339
No log	3.3333	10	0.6456	0.0120	0.7020
No log	4.0	12	0.7331	0.0	0.7912
No log	4.6667	14	0.7761	0.0	0.8325
No log	5.3333	16	0.6870	0.0	0.7416
No log	6.0	18	0.6157	0.0	0.6661
No log	6.6667	20	0.5690	0.0120	0.6176
No log	7.3333	22	0.5419	0.1646	0.5867
No log	8.0	24	0.5390	0.1646	0.5830
No log	8.6667	26	0.5477	0.0120	0.5917
No log	9.3333	28	0.5587	0.0120	0.6034
No log	10.0	30	0.5660	0.0120	0.6114

Framework versions

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