arabert_baseline_development_task5_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: 0.5703
• Qwk: 0.7312
• Mse: 0.5703

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	0.3333	2	2.7370	-0.0412	2.7370
No log	0.6667	4	1.1106	0.0254	1.1106
No log	1.0	6	0.8018	0.3448	0.8018
No log	1.3333	8	0.7112	0.4203	0.7112
No log	1.6667	10	0.7153	0.2778	0.7153
No log	2.0	12	0.6181	0.3333	0.6181
No log	2.3333	14	0.5263	0.4379	0.5263
No log	2.6667	16	0.5056	0.4444	0.5056
No log	3.0	18	0.4721	0.4318	0.4721
No log	3.3333	20	0.4560	0.5251	0.4560
No log	3.6667	22	0.4550	0.5506	0.4550
No log	4.0	24	0.5190	0.7399	0.5190
No log	4.3333	26	0.5822	0.7568	0.5822
No log	4.6667	28	0.5363	0.6328	0.5363
No log	5.0	30	0.5203	0.4382	0.5203
No log	5.3333	32	0.5859	0.4388	0.5859
No log	5.6667	34	0.5248	0.3956	0.5248
No log	6.0	36	0.5042	0.5977	0.5042
No log	6.3333	38	0.5446	0.6667	0.5446
No log	6.6667	40	0.5984	0.7312	0.5984
No log	7.0	42	0.6002	0.7312	0.6002
No log	7.3333	44	0.5662	0.7312	0.5662
No log	7.6667	46	0.5376	0.6667	0.5376
No log	8.0	48	0.5417	0.6667	0.5417
No log	8.3333	50	0.5612	0.7312	0.5612
No log	8.6667	52	0.5739	0.7312	0.5739
No log	9.0	54	0.5740	0.7312	0.5740
No log	9.3333	56	0.5707	0.7312	0.5707
No log	9.6667	58	0.5714	0.7312	0.5714
No log	10.0	60	0.5703	0.7312	0.5703

Framework versions

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