arabert_baseline_style_task1_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: 0.4377
• Qwk: 0.6828
• Mse: 0.4377

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
No log	0.1818	2	4.4784	-0.0081	4.4784
No log	0.3636	4	2.3099	-0.0153	2.3099
No log	0.5455	6	1.3163	0.0558	1.3163
No log	0.7273	8	0.8819	-0.0221	0.8819
No log	0.9091	10	0.6487	0.1135	0.6487
No log	1.0909	12	0.5998	0.2851	0.5998
No log	1.2727	14	0.7188	0.0056	0.7188
No log	1.4545	16	0.8344	-0.0825	0.8344
No log	1.6364	18	0.6626	0.0937	0.6626
No log	1.8182	20	0.6124	0.1135	0.6124
No log	2.0	22	0.4790	0.3713	0.4790
No log	2.1818	24	0.4866	0.2794	0.4866
No log	2.3636	26	0.4908	0.2794	0.4908
No log	2.5455	28	0.4873	0.2794	0.4873
No log	2.7273	30	0.4863	0.1868	0.4863
No log	2.9091	32	0.4641	0.1868	0.4641
No log	3.0909	34	0.4075	0.3713	0.4075
No log	3.2727	36	0.4063	0.4146	0.4063
No log	3.4545	38	0.4231	0.4146	0.4231
No log	3.6364	40	0.4760	0.3810	0.4760
No log	3.8182	42	0.5071	0.3810	0.5071
No log	4.0	44	0.4729	0.4425	0.4729
No log	4.1818	46	0.4572	0.4425	0.4572
No log	4.3636	48	0.4364	0.4140	0.4364
No log	4.5455	50	0.4316	0.3427	0.4316
No log	4.7273	52	0.4451	0.4894	0.4451
No log	4.9091	54	0.4293	0.4734	0.4293
No log	5.0909	56	0.4505	0.5517	0.4505
No log	5.2727	58	0.5710	0.5940	0.5710
No log	5.4545	60	0.6188	0.4371	0.6188
No log	5.6364	62	0.5507	0.5011	0.5507
No log	5.8182	64	0.5078	0.56	0.5078
No log	6.0	66	0.4649	0.5299	0.4649
No log	6.1818	68	0.4399	0.5084	0.4399
No log	6.3636	70	0.4437	0.5084	0.4437
No log	6.5455	72	0.4552	0.5258	0.4552
No log	6.7273	74	0.4396	0.4634	0.4396
No log	6.9091	76	0.4371	0.4634	0.4371
No log	7.0909	78	0.4213	0.5922	0.4213
No log	7.2727	80	0.4056	0.5922	0.4056
No log	7.4545	82	0.3976	0.5772	0.3976
No log	7.6364	84	0.3977	0.6602	0.3977
No log	7.8182	86	0.4154	0.6818	0.4154
No log	8.0	88	0.4352	0.6294	0.4352
No log	8.1818	90	0.4402	0.6780	0.4402
No log	8.3636	92	0.4551	0.6367	0.4551
No log	8.5455	94	0.4759	0.5009	0.4759
No log	8.7273	96	0.4899	0.5009	0.4899
No log	8.9091	98	0.4994	0.5484	0.4994
No log	9.0909	100	0.4880	0.6791	0.4880
No log	9.2727	102	0.4730	0.6791	0.4730
No log	9.4545	104	0.4591	0.6828	0.4591
No log	9.6364	106	0.4493	0.6828	0.4493
No log	9.8182	108	0.4415	0.6828	0.4415
No log	10.0	110	0.4377	0.6828	0.4377

Framework versions

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