arabert_baseline_relevance_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: 0.1845
• Qwk: 0.3789
• Mse: 0.1845

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	0.7186	-0.0682	0.7186
No log	0.6667	4	0.2563	0.0	0.2563
No log	1.0	6	0.1977	0.0551	0.1977
No log	1.3333	8	0.1845	0.2373	0.1845
No log	1.6667	10	0.1961	0.2361	0.1961
No log	2.0	12	0.2108	0.1960	0.2108
No log	2.3333	14	0.2096	0.2347	0.2096
No log	2.6667	16	0.2117	0.2814	0.2117
No log	3.0	18	0.2125	0.2814	0.2125
No log	3.3333	20	0.2086	0.3789	0.2086
No log	3.6667	22	0.2136	0.2547	0.2136
No log	4.0	24	0.2106	0.3293	0.2106
No log	4.3333	26	0.1994	0.3293	0.1994
No log	4.6667	28	0.1978	0.1477	0.1978
No log	5.0	30	0.2011	0.2353	0.2011
No log	5.3333	32	0.2091	0.2258	0.2091
No log	5.6667	34	0.2215	0.2763	0.2215
No log	6.0	36	0.2177	0.2763	0.2177
No log	6.3333	38	0.2103	0.2763	0.2103
No log	6.6667	40	0.1968	0.4304	0.1968
No log	7.0	42	0.1868	0.3789	0.1868
No log	7.3333	44	0.1820	0.3789	0.1820
No log	7.6667	46	0.1813	0.3789	0.1813
No log	8.0	48	0.1828	0.3789	0.1828
No log	8.3333	50	0.1865	0.3789	0.1865
No log	8.6667	52	0.1900	0.4304	0.1900
No log	9.0	54	0.1886	0.4304	0.1886
No log	9.3333	56	0.1873	0.3789	0.1873
No log	9.6667	58	0.1853	0.3789	0.1853
No log	10.0	60	0.1845	0.3789	0.1845

Framework versions

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