ArabicNewSplits6_FineTuningAraBERT_run3_AugV5_k3_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: 0.8622
• Qwk: 0.4710
• Mse: 0.8622
• Rmse: 0.9286

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	0.1176	2	3.9747	-0.0187	3.9747	1.9937
No log	0.2353	4	1.9391	0.0601	1.9391	1.3925
No log	0.3529	6	1.1241	0.0460	1.1241	1.0602
No log	0.4706	8	0.9166	-0.0387	0.9166	0.9574
No log	0.5882	10	0.7253	0.1532	0.7253	0.8517
No log	0.7059	12	0.9489	0.0109	0.9489	0.9741
No log	0.8235	14	1.4064	0.0834	1.4064	1.1859
No log	0.9412	16	1.7137	0.1183	1.7137	1.3091
No log	1.0588	18	1.2873	0.0959	1.2873	1.1346
No log	1.1765	20	0.7776	0.1599	0.7776	0.8818
No log	1.2941	22	0.6403	0.2645	0.6403	0.8002
No log	1.4118	24	0.7953	0.0851	0.7953	0.8918
No log	1.5294	26	0.9240	-0.2565	0.9240	0.9612
No log	1.6471	28	0.8305	-0.0594	0.8305	0.9113
No log	1.7647	30	0.7121	0.2061	0.7121	0.8438
No log	1.8824	32	0.6822	0.3170	0.6822	0.8260
No log	2.0	34	0.7299	0.1887	0.7299	0.8543
No log	2.1176	36	0.7259	0.2617	0.7259	0.8520
No log	2.2353	38	0.7089	0.2694	0.7089	0.8420
No log	2.3529	40	0.7216	0.2571	0.7216	0.8495
No log	2.4706	42	0.7910	0.1213	0.7910	0.8894
No log	2.5882	44	0.8115	0.1139	0.8115	0.9008
No log	2.7059	46	0.7476	0.2255	0.7476	0.8647
No log	2.8235	48	0.6516	0.3271	0.6516	0.8072
No log	2.9412	50	0.6081	0.3021	0.6081	0.7798
No log	3.0588	52	0.5996	0.3429	0.5996	0.7744
No log	3.1765	54	0.6014	0.3773	0.6014	0.7755
No log	3.2941	56	0.5967	0.4366	0.5967	0.7725
No log	3.4118	58	0.5947	0.4651	0.5947	0.7712
No log	3.5294	60	0.6476	0.3556	0.6476	0.8047
No log	3.6471	62	0.6694	0.3114	0.6694	0.8182
No log	3.7647	64	0.6288	0.4040	0.6288	0.7929
No log	3.8824	66	0.6215	0.3932	0.6215	0.7883
No log	4.0	68	0.6030	0.4498	0.6030	0.7766
No log	4.1176	70	0.5816	0.4865	0.5816	0.7626
No log	4.2353	72	0.5866	0.4898	0.5866	0.7659
No log	4.3529	74	0.6041	0.5108	0.6041	0.7772
No log	4.4706	76	0.6344	0.4551	0.6344	0.7965
No log	4.5882	78	0.6656	0.3525	0.6656	0.8159
No log	4.7059	80	0.6617	0.4107	0.6617	0.8134
No log	4.8235	82	0.6623	0.3952	0.6623	0.8138
No log	4.9412	84	0.6761	0.4833	0.6761	0.8223
No log	5.0588	86	0.7155	0.4539	0.7155	0.8459
No log	5.1765	88	0.7377	0.4261	0.7377	0.8589
No log	5.2941	90	0.7658	0.3670	0.7658	0.8751
No log	5.4118	92	0.7913	0.3723	0.7913	0.8896
No log	5.5294	94	0.8054	0.4019	0.8054	0.8975
No log	5.6471	96	0.7966	0.4015	0.7966	0.8925
No log	5.7647	98	0.7813	0.4400	0.7813	0.8839
No log	5.8824	100	0.7903	0.4603	0.7903	0.8890
No log	6.0	102	0.7920	0.4812	0.7920	0.8900
No log	6.1176	104	0.8044	0.4782	0.8044	0.8969
No log	6.2353	106	0.8138	0.4820	0.8138	0.9021
No log	6.3529	108	0.8133	0.4820	0.8133	0.9018
No log	6.4706	110	0.8122	0.4782	0.8122	0.9012
No log	6.5882	112	0.8231	0.4860	0.8231	0.9073
No log	6.7059	114	0.8303	0.4842	0.8303	0.9112
No log	6.8235	116	0.8364	0.4704	0.8364	0.9146
No log	6.9412	118	0.8444	0.4699	0.8444	0.9189
No log	7.0588	120	0.8440	0.4592	0.8440	0.9187
No log	7.1765	122	0.8434	0.4596	0.8434	0.9184
No log	7.2941	124	0.8334	0.4838	0.8334	0.9129
No log	7.4118	126	0.8373	0.4838	0.8373	0.9151
No log	7.5294	128	0.8455	0.4831	0.8455	0.9195
No log	7.6471	130	0.8541	0.4666	0.8541	0.9242
No log	7.7647	132	0.8588	0.4588	0.8588	0.9267
No log	7.8824	134	0.8691	0.4581	0.8691	0.9323
No log	8.0	136	0.8735	0.4581	0.8735	0.9346
No log	8.1176	138	0.8763	0.4694	0.8763	0.9361
No log	8.2353	140	0.8716	0.4694	0.8716	0.9336
No log	8.3529	142	0.8634	0.4602	0.8634	0.9292
No log	8.4706	144	0.8506	0.4697	0.8506	0.9223
No log	8.5882	146	0.8399	0.4931	0.8399	0.9165
No log	8.7059	148	0.8389	0.4876	0.8389	0.9159
No log	8.8235	150	0.8378	0.4883	0.8378	0.9153
No log	8.9412	152	0.8414	0.4931	0.8414	0.9173
No log	9.0588	154	0.8471	0.4853	0.8471	0.9204
No log	9.1765	156	0.8519	0.4606	0.8519	0.9230
No log	9.2941	158	0.8567	0.4722	0.8567	0.9256
No log	9.4118	160	0.8607	0.4710	0.8607	0.9277
No log	9.5294	162	0.8632	0.4704	0.8632	0.9291
No log	9.6471	164	0.8638	0.4704	0.8638	0.9294
No log	9.7647	166	0.8633	0.4704	0.8633	0.9291
No log	9.8824	168	0.8626	0.4704	0.8626	0.9288
No log	10.0	170	0.8622	0.4710	0.8622	0.9286

Framework versions

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