arabert_baseline_relevance_task4_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: 0.0752
• Qwk: 0.0
• Mse: 0.0752

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	1.0	2	0.4061	0.0	0.4061
No log	2.0	4	0.1232	0.0	0.1232
No log	3.0	6	0.1020	0.0	0.1020
No log	4.0	8	0.1130	0.0400	0.1130
No log	5.0	10	0.1198	0.0	0.1198
No log	6.0	12	0.1295	0.0	0.1295
No log	7.0	14	0.1092	0.0	0.1092
No log	8.0	16	0.0901	0.0	0.0901
No log	9.0	18	0.0786	0.0	0.0786
No log	10.0	20	0.0752	0.0	0.0752

Framework versions

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