ArabicNewSplits4_WithDuplicationsForScore5_FineTuningAraBERT_run1_AugV5_k1_task2_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: 0.8383
• Qwk: 0.4561
• Mse: 0.8383
• Rmse: 0.9156

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	0.2222	2	2.1080	0.0630	2.1080	1.4519
No log	0.4444	4	0.9353	0.0946	0.9353	0.9671
No log	0.6667	6	0.9070	-0.1013	0.9070	0.9524
No log	0.8889	8	0.8541	0.0707	0.8541	0.9242
No log	1.1111	10	1.0388	0.0372	1.0388	1.0192
No log	1.3333	12	1.0301	0.0517	1.0301	1.0149
No log	1.5556	14	0.9671	0.0754	0.9671	0.9834
No log	1.7778	16	0.7910	0.0918	0.7910	0.8894
No log	2.0	18	0.6729	0.2053	0.6729	0.8203
No log	2.2222	20	0.6513	0.2686	0.6513	0.8071
No log	2.4444	22	0.6344	0.2729	0.6344	0.7965
No log	2.6667	24	0.6299	0.2552	0.6299	0.7936
No log	2.8889	26	0.6483	0.2053	0.6483	0.8052
No log	3.1111	28	0.6801	0.2477	0.6801	0.8247
No log	3.3333	30	0.6295	0.3329	0.6295	0.7934
No log	3.5556	32	0.6036	0.3776	0.6036	0.7769
No log	3.7778	34	0.6518	0.3197	0.6518	0.8073
No log	4.0	36	0.6971	0.3301	0.6971	0.8349
No log	4.2222	38	0.7707	0.2609	0.7707	0.8779
No log	4.4444	40	0.7285	0.3262	0.7285	0.8535
No log	4.6667	42	0.6153	0.4126	0.6153	0.7844
No log	4.8889	44	0.5811	0.4818	0.5811	0.7623
No log	5.1111	46	0.5852	0.5126	0.5852	0.7650
No log	5.3333	48	0.6347	0.3885	0.6347	0.7967
No log	5.5556	50	0.7781	0.3580	0.7781	0.8821
No log	5.7778	52	0.8404	0.3516	0.8404	0.9168
No log	6.0	54	0.7850	0.4099	0.7850	0.8860
No log	6.2222	56	0.7416	0.3769	0.7416	0.8612
No log	6.4444	58	0.7781	0.3688	0.7781	0.8821
No log	6.6667	60	0.8545	0.3776	0.8545	0.9244
No log	6.8889	62	0.8611	0.3906	0.8611	0.9279
No log	7.1111	64	0.7903	0.3806	0.7903	0.8890
No log	7.3333	66	0.7593	0.4075	0.7593	0.8714
No log	7.5556	68	0.7633	0.3981	0.7633	0.8737
No log	7.7778	70	0.7855	0.3987	0.7855	0.8863
No log	8.0	72	0.7885	0.4430	0.7885	0.8880
No log	8.2222	74	0.8118	0.4508	0.8118	0.9010
No log	8.4444	76	0.8189	0.4319	0.8189	0.9049
No log	8.6667	78	0.8215	0.4549	0.8215	0.9064
No log	8.8889	80	0.8147	0.4433	0.8147	0.9026
No log	9.1111	82	0.8113	0.4433	0.8113	0.9007
No log	9.3333	84	0.8084	0.4435	0.8084	0.8991
No log	9.5556	86	0.8164	0.4433	0.8164	0.9036
No log	9.7778	88	0.8298	0.4561	0.8298	0.9110
No log	10.0	90	0.8383	0.4561	0.8383	0.9156

Framework versions

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