ArabicNewSplits6_FineTuningAraBERT_run3_AugV5_k1_task5_organization

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: 1.1701
• Qwk: 0.6058
• Mse: 1.1701
• Rmse: 1.0817

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: 8
• eval_batch_size: 8
• 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	Rmse
No log	0.3333	2	2.2270	0.0404	2.2270	1.4923
No log	0.6667	4	1.7033	0.1038	1.7033	1.3051
No log	1.0	6	1.2518	0.2634	1.2518	1.1188
No log	1.3333	8	1.4697	0.3516	1.4697	1.2123
No log	1.6667	10	1.8177	0.2488	1.8177	1.3482
No log	2.0	12	1.9450	0.2528	1.9450	1.3946
No log	2.3333	14	1.7963	0.2832	1.7963	1.3402
No log	2.6667	16	1.6635	0.3767	1.6635	1.2898
No log	3.0	18	1.6466	0.3692	1.6466	1.2832
No log	3.3333	20	1.4279	0.4503	1.4279	1.1950
No log	3.6667	22	1.2865	0.4822	1.2865	1.1342
No log	4.0	24	1.1275	0.5264	1.1275	1.0618
No log	4.3333	26	1.0850	0.5376	1.0850	1.0416
No log	4.6667	28	1.1906	0.5247	1.1906	1.0911
No log	5.0	30	1.2572	0.5978	1.2572	1.1212
No log	5.3333	32	1.2135	0.6099	1.2135	1.1016
No log	5.6667	34	1.0371	0.6206	1.0371	1.0184
No log	6.0	36	1.0359	0.6146	1.0359	1.0178
No log	6.3333	38	1.0582	0.6336	1.0582	1.0287
No log	6.6667	40	1.2419	0.6184	1.2419	1.1144
No log	7.0	42	1.4593	0.5727	1.4593	1.2080
No log	7.3333	44	1.4426	0.5701	1.4426	1.2011
No log	7.6667	46	1.3964	0.5653	1.3964	1.1817
No log	8.0	48	1.2396	0.6172	1.2396	1.1134
No log	8.3333	50	1.0763	0.6367	1.0763	1.0374
No log	8.6667	52	1.0572	0.6454	1.0572	1.0282
No log	9.0	54	1.1078	0.6340	1.1078	1.0525
No log	9.3333	56	1.1352	0.6193	1.1352	1.0655
No log	9.6667	58	1.1583	0.6042	1.1583	1.0763
No log	10.0	60	1.1701	0.6058	1.1701	1.0817

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.0+cu118
• Datasets 2.21.0
• Tokenizers 0.19.1