arabert_baseline_relevance_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: 0.2326
• Qwk: 0.0
• Mse: 0.2326

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	0.5604	-0.0845	0.5490
No log	1.3333	4	0.4316	0.0000	0.4136
No log	2.0	6	0.4602	-0.1579	0.4699
No log	2.6667	8	0.2569	0.0294	0.2631
No log	3.3333	10	0.2323	0.0	0.2316
No log	4.0	12	0.3209	0.0	0.3171
No log	4.6667	14	0.2901	0.0	0.2877
No log	5.3333	16	0.2432	0.0	0.2433
No log	6.0	18	0.2222	0.0	0.2222
No log	6.6667	20	0.2264	0.0	0.2257
No log	7.3333	22	0.2342	0.0	0.2329
No log	8.0	24	0.2393	0.0	0.2375
No log	8.6667	26	0.2361	0.0	0.2351
No log	9.3333	28	0.2342	0.0	0.2338
No log	10.0	30	0.2326	0.0	0.2326

Framework versions

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