ArabicNewSplits6_WithDuplicationsForScore5_FineTuningAraBERT_run2_AugV5_k6_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: 0.9463
• Qwk: 0.4689
• Mse: 0.9463
• Rmse: 0.9728

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	0.0556	2	3.9018	-0.0114	3.9018	1.9753
No log	0.1111	4	3.3916	0.0186	3.3916	1.8416
No log	0.1667	6	1.9437	0.0985	1.9437	1.3942
No log	0.2222	8	1.0629	0.0296	1.0629	1.0310
No log	0.2778	10	0.9121	0.0524	0.9121	0.9550
No log	0.3333	12	1.3299	-0.0415	1.3299	1.1532
No log	0.3889	14	0.9460	-0.0402	0.9460	0.9726
No log	0.4444	16	0.7531	0.0841	0.7531	0.8678
No log	0.5	18	0.7986	0.0918	0.7986	0.8937
No log	0.5556	20	0.8091	0.0387	0.8091	0.8995
No log	0.6111	22	0.7568	0.0939	0.7568	0.8700
No log	0.6667	24	0.7598	0.0804	0.7598	0.8717
No log	0.7222	26	0.8006	0.1676	0.8006	0.8948
No log	0.7778	28	0.6971	0.2692	0.6971	0.8349
No log	0.8333	30	0.6410	0.2413	0.6410	0.8006
No log	0.8889	32	0.6303	0.2326	0.6303	0.7939
No log	0.9444	34	0.6167	0.2671	0.6167	0.7853
No log	1.0	36	0.5989	0.3725	0.5989	0.7739
No log	1.0556	38	0.7605	0.2926	0.7605	0.8721
No log	1.1111	40	0.7636	0.3041	0.7636	0.8738
No log	1.1667	42	0.6013	0.4011	0.6013	0.7754
No log	1.2222	44	0.6906	0.4553	0.6906	0.8310
No log	1.2778	46	0.8940	0.3589	0.8940	0.9455
No log	1.3333	48	0.7924	0.4382	0.7924	0.8902
No log	1.3889	50	0.6775	0.4573	0.6775	0.8231
No log	1.4444	52	0.6695	0.4392	0.6695	0.8182
No log	1.5	54	0.6983	0.5155	0.6983	0.8356
No log	1.5556	56	0.7390	0.5019	0.7390	0.8596
No log	1.6111	58	0.6695	0.4905	0.6695	0.8182
No log	1.6667	60	0.6748	0.4305	0.6748	0.8215
No log	1.7222	62	0.7521	0.5127	0.7521	0.8672
No log	1.7778	64	0.8725	0.4361	0.8725	0.9341
No log	1.8333	66	0.8467	0.4685	0.8467	0.9202
No log	1.8889	68	0.8471	0.4015	0.8471	0.9204
No log	1.9444	70	0.7251	0.4388	0.7251	0.8515
No log	2.0	72	0.7365	0.4307	0.7365	0.8582
No log	2.0556	74	0.7375	0.4261	0.7375	0.8588
No log	2.1111	76	0.9043	0.4517	0.9043	0.9509
No log	2.1667	78	1.0735	0.3685	1.0735	1.0361
No log	2.2222	80	1.0133	0.3826	1.0133	1.0066
No log	2.2778	82	0.8582	0.4743	0.8582	0.9264
No log	2.3333	84	0.8607	0.4677	0.8607	0.9278
No log	2.3889	86	0.7798	0.4697	0.7798	0.8831
No log	2.4444	88	0.7476	0.4517	0.7476	0.8646
No log	2.5	90	0.7304	0.4554	0.7304	0.8546
No log	2.5556	92	0.7960	0.4592	0.7960	0.8922
No log	2.6111	94	0.8201	0.4601	0.8201	0.9056
No log	2.6667	96	0.7987	0.4886	0.7987	0.8937
No log	2.7222	98	0.7133	0.4987	0.7133	0.8446
No log	2.7778	100	0.7194	0.4975	0.7194	0.8482
No log	2.8333	102	0.9219	0.4862	0.9219	0.9601
No log	2.8889	104	0.9707	0.4841	0.9707	0.9853
No log	2.9444	106	0.8769	0.4804	0.8769	0.9364
No log	3.0	108	0.8304	0.4912	0.8304	0.9112
No log	3.0556	110	0.8193	0.4873	0.8193	0.9051
No log	3.1111	112	0.7695	0.4915	0.7695	0.8772
No log	3.1667	114	0.7933	0.4859	0.7933	0.8907
No log	3.2222	116	0.8754	0.4902	0.8754	0.9356
No log	3.2778	118	0.9513	0.4894	0.9513	0.9753
No log	3.3333	120	0.8587	0.4661	0.8587	0.9267
No log	3.3889	122	0.8180	0.4842	0.8180	0.9044
No log	3.4444	124	0.8644	0.4695	0.8644	0.9297
No log	3.5	126	1.1261	0.4384	1.1261	1.0612
No log	3.5556	128	1.6010	0.3710	1.6010	1.2653
No log	3.6111	130	1.5837	0.3831	1.5837	1.2584
No log	3.6667	132	1.2811	0.4356	1.2811	1.1318
No log	3.7222	134	0.9411	0.4909	0.9411	0.9701
No log	3.7778	136	0.8985	0.4818	0.8985	0.9479
No log	3.8333	138	0.8407	0.4745	0.8407	0.9169
No log	3.8889	140	0.8385	0.4719	0.8385	0.9157
No log	3.9444	142	0.9046	0.4998	0.9046	0.9511
No log	4.0	144	0.9801	0.4365	0.9801	0.9900
No log	4.0556	146	0.9476	0.4106	0.9476	0.9735
No log	4.1111	148	0.8129	0.5032	0.8129	0.9016
No log	4.1667	150	0.7671	0.5426	0.7671	0.8758
No log	4.2222	152	0.7928	0.5351	0.7928	0.8904
No log	4.2778	154	0.8187	0.5077	0.8187	0.9048
No log	4.3333	156	0.8483	0.5077	0.8483	0.9210
No log	4.3889	158	0.8784	0.5189	0.8784	0.9372
No log	4.4444	160	0.8945	0.4941	0.8945	0.9458
No log	4.5	162	0.8872	0.4968	0.8872	0.9419
No log	4.5556	164	0.9553	0.5071	0.9553	0.9774
No log	4.6111	166	1.2111	0.4827	1.2111	1.1005
No log	4.6667	168	1.5180	0.3921	1.5180	1.2321
No log	4.7222	170	1.5750	0.3817	1.5750	1.2550
No log	4.7778	172	1.4590	0.4184	1.4590	1.2079
No log	4.8333	174	1.1956	0.4822	1.1956	1.0934
No log	4.8889	176	0.9507	0.4840	0.9507	0.9750
No log	4.9444	178	0.8719	0.4913	0.8719	0.9338
No log	5.0	180	0.8428	0.4832	0.8428	0.9181
No log	5.0556	182	0.8779	0.5062	0.8779	0.9370
No log	5.1111	184	1.0324	0.4716	1.0324	1.0161
No log	5.1667	186	1.3382	0.4502	1.3382	1.1568
No log	5.2222	188	1.4359	0.4346	1.4359	1.1983
No log	5.2778	190	1.2655	0.4544	1.2655	1.1249
No log	5.3333	192	0.9978	0.4803	0.9978	0.9989
No log	5.3889	194	0.9287	0.4784	0.9287	0.9637
No log	5.4444	196	0.9498	0.5162	0.9498	0.9746
No log	5.5	198	0.9587	0.5069	0.9587	0.9791
No log	5.5556	200	0.9371	0.5069	0.9371	0.9680
No log	5.6111	202	0.9425	0.5146	0.9425	0.9708
No log	5.6667	204	0.8905	0.4953	0.8905	0.9437
No log	5.7222	206	0.8640	0.5062	0.8640	0.9295
No log	5.7778	208	0.8615	0.5122	0.8615	0.9282
No log	5.8333	210	0.8981	0.5002	0.8981	0.9477
No log	5.8889	212	0.9612	0.4830	0.9612	0.9804
No log	5.9444	214	0.9391	0.4945	0.9391	0.9691
No log	6.0	216	0.8401	0.4756	0.8401	0.9166
No log	6.0556	218	0.7823	0.4784	0.7823	0.8845
No log	6.1111	220	0.8053	0.4426	0.8053	0.8974
No log	6.1667	222	0.8818	0.4541	0.8818	0.9390
No log	6.2222	224	0.9189	0.4526	0.9189	0.9586
No log	6.2778	226	0.9535	0.4692	0.9535	0.9765
No log	6.3333	228	1.0614	0.4978	1.0614	1.0302
No log	6.3889	230	1.2249	0.4232	1.2249	1.1067
No log	6.4444	232	1.3073	0.4624	1.3073	1.1434
No log	6.5	234	1.2680	0.4477	1.2680	1.1260
No log	6.5556	236	1.1987	0.4657	1.1987	1.0948
No log	6.6111	238	1.0835	0.4764	1.0835	1.0409
No log	6.6667	240	1.0109	0.4835	1.0109	1.0054
No log	6.7222	242	0.9797	0.4863	0.9797	0.9898
No log	6.7778	244	0.9619	0.4831	0.9619	0.9808
No log	6.8333	246	0.9964	0.5054	0.9964	0.9982
No log	6.8889	248	1.0203	0.4931	1.0203	1.0101
No log	6.9444	250	1.0616	0.4692	1.0616	1.0303
No log	7.0	252	1.0471	0.4708	1.0471	1.0233
No log	7.0556	254	1.0339	0.5009	1.0339	1.0168
No log	7.1111	256	1.0523	0.4908	1.0523	1.0258
No log	7.1667	258	1.1064	0.4657	1.1064	1.0519
No log	7.2222	260	1.1125	0.4552	1.1125	1.0548
No log	7.2778	262	1.0911	0.4552	1.0911	1.0446
No log	7.3333	264	1.0684	0.4600	1.0684	1.0336
No log	7.3889	266	1.0064	0.4726	1.0064	1.0032
No log	7.4444	268	0.9102	0.5187	0.9102	0.9540
No log	7.5	270	0.8597	0.5256	0.8597	0.9272
No log	7.5556	272	0.8411	0.5256	0.8411	0.9171
No log	7.6111	274	0.8359	0.4976	0.8359	0.9143
No log	7.6667	276	0.8531	0.4873	0.8531	0.9236
No log	7.7222	278	0.8694	0.4800	0.8694	0.9324
No log	7.7778	280	0.9298	0.4875	0.9298	0.9643
No log	7.8333	282	0.9899	0.4513	0.9899	0.9949
No log	7.8889	284	1.0089	0.4511	1.0089	1.0044
No log	7.9444	286	0.9881	0.4626	0.9881	0.9940
No log	8.0	288	0.9290	0.4905	0.9290	0.9639
No log	8.0556	290	0.9045	0.4638	0.9045	0.9511
No log	8.1111	292	0.8812	0.4968	0.8812	0.9387
No log	8.1667	294	0.8992	0.4912	0.8992	0.9483
No log	8.2222	296	0.9401	0.4894	0.9401	0.9696
No log	8.2778	298	1.0009	0.4706	1.0009	1.0005
No log	8.3333	300	1.0487	0.4629	1.0487	1.0240
No log	8.3889	302	1.0739	0.4629	1.0739	1.0363
No log	8.4444	304	1.0417	0.4633	1.0417	1.0206
No log	8.5	306	0.9724	0.4639	0.9724	0.9861
No log	8.5556	308	0.9234	0.4781	0.9234	0.9609
No log	8.6111	310	0.9082	0.4781	0.9082	0.9530
No log	8.6667	312	0.9175	0.4781	0.9175	0.9579
No log	8.7222	314	0.9389	0.4770	0.9389	0.9689
No log	8.7778	316	0.9462	0.4817	0.9462	0.9727
No log	8.8333	318	0.9598	0.4812	0.9598	0.9797
No log	8.8889	320	0.9917	0.4900	0.9917	0.9958
No log	8.9444	322	1.0022	0.4681	1.0022	1.0011
No log	9.0	324	0.9984	0.4681	0.9984	0.9992
No log	9.0556	326	0.9916	0.4746	0.9916	0.9958
No log	9.1111	328	0.9667	0.4770	0.9667	0.9832
No log	9.1667	330	0.9587	0.4882	0.9587	0.9791
No log	9.2222	332	0.9491	0.4836	0.9491	0.9742
No log	9.2778	334	0.9437	0.4717	0.9437	0.9715
No log	9.3333	336	0.9345	0.4775	0.9345	0.9667
No log	9.3889	338	0.9397	0.4717	0.9397	0.9694
No log	9.4444	340	0.9570	0.4865	0.9570	0.9782
No log	9.5	342	0.9759	0.4721	0.9759	0.9879
No log	9.5556	344	0.9828	0.4716	0.9828	0.9914
No log	9.6111	346	0.9824	0.4716	0.9824	0.9912
No log	9.6667	348	0.9796	0.4716	0.9796	0.9897
No log	9.7222	350	0.9725	0.4716	0.9725	0.9862
No log	9.7778	352	0.9650	0.4721	0.9650	0.9823
No log	9.8333	354	0.9595	0.4721	0.9595	0.9796
No log	9.8889	356	0.9533	0.4844	0.9533	0.9764
No log	9.9444	358	0.9483	0.4844	0.9483	0.9738
No log	10.0	360	0.9463	0.4689	0.9463	0.9728

Framework versions

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