ArabicNewSplits6_FineTuningAraBERTFreeze_run3_AugV5_k2_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: 0.9546
• Qwk: 0.4713
• Mse: 0.9546
• Rmse: 0.9770

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: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	0.2857	2	6.3965	-0.0278	6.3966	2.5291
No log	0.5714	4	4.2632	-0.0253	4.2632	2.0647
No log	0.8571	6	2.9354	0.0309	2.9354	1.7133
No log	1.1429	8	2.0589	0.0457	2.0589	1.4349
No log	1.4286	10	1.3639	0.1123	1.3639	1.1679
No log	1.7143	12	0.9644	0.0640	0.9644	0.9821
No log	2.0	14	0.7994	0.1170	0.7994	0.8941
No log	2.2857	16	0.7457	0.1591	0.7457	0.8636
No log	2.5714	18	0.6973	0.2693	0.6973	0.8350
No log	2.8571	20	0.6474	0.2968	0.6474	0.8046
No log	3.1429	22	0.6350	0.3222	0.6350	0.7968
No log	3.4286	24	0.6536	0.2463	0.6536	0.8085
No log	3.7143	26	0.6852	0.2333	0.6852	0.8278
No log	4.0	28	0.7400	0.2253	0.7400	0.8602
No log	4.2857	30	0.7424	0.2333	0.7424	0.8616
No log	4.5714	32	0.7056	0.2532	0.7056	0.8400
No log	4.8571	34	0.6967	0.2175	0.6967	0.8347
No log	5.1429	36	0.6623	0.3058	0.6623	0.8138
No log	5.4286	38	0.6141	0.4405	0.6141	0.7836
No log	5.7143	40	0.5823	0.4037	0.5823	0.7631
No log	6.0	42	0.5719	0.4250	0.5719	0.7563
No log	6.2857	44	0.5665	0.4192	0.5665	0.7527
No log	6.5714	46	0.5733	0.3697	0.5733	0.7572
No log	6.8571	48	0.5755	0.3969	0.5755	0.7586
No log	7.1429	50	0.5786	0.4373	0.5786	0.7607
No log	7.4286	52	0.5667	0.4429	0.5667	0.7528
No log	7.7143	54	0.5547	0.4400	0.5547	0.7448
No log	8.0	56	0.5559	0.4429	0.5559	0.7456
No log	8.2857	58	0.5573	0.4759	0.5573	0.7466
No log	8.5714	60	0.5657	0.4676	0.5657	0.7521
No log	8.8571	62	0.5593	0.4400	0.5593	0.7479
No log	9.1429	64	0.5568	0.4478	0.5568	0.7462
No log	9.4286	66	0.5511	0.4669	0.5511	0.7424
No log	9.7143	68	0.5458	0.4751	0.5458	0.7388
No log	10.0	70	0.5573	0.4794	0.5573	0.7465
No log	10.2857	72	0.5512	0.4688	0.5512	0.7424
No log	10.5714	74	0.5467	0.4968	0.5467	0.7394
No log	10.8571	76	0.5639	0.4916	0.5639	0.7510
No log	11.1429	78	0.5714	0.4665	0.5714	0.7559
No log	11.4286	80	0.5927	0.4609	0.5927	0.7699
No log	11.7143	82	0.6054	0.4707	0.6054	0.7781
No log	12.0	84	0.5673	0.4629	0.5673	0.7532
No log	12.2857	86	0.5550	0.5254	0.5550	0.7450
No log	12.5714	88	0.5539	0.5283	0.5539	0.7443
No log	12.8571	90	0.5769	0.5416	0.5769	0.7595
No log	13.1429	92	0.5996	0.5128	0.5996	0.7743
No log	13.4286	94	0.6222	0.4979	0.6222	0.7888
No log	13.7143	96	0.6616	0.4473	0.6616	0.8134
No log	14.0	98	0.6695	0.4799	0.6695	0.8182
No log	14.2857	100	0.6621	0.4844	0.6621	0.8137
No log	14.5714	102	0.6780	0.4703	0.6780	0.8234
No log	14.8571	104	0.6962	0.4796	0.6962	0.8344
No log	15.1429	106	0.6530	0.5471	0.6530	0.8081
No log	15.4286	108	0.6211	0.5585	0.6211	0.7881
No log	15.7143	110	0.6305	0.5504	0.6305	0.7940
No log	16.0	112	0.6818	0.5243	0.6818	0.8257
No log	16.2857	114	0.7240	0.5051	0.7240	0.8509
No log	16.5714	116	0.7598	0.4815	0.7598	0.8717
No log	16.8571	118	0.7529	0.4991	0.7529	0.8677
No log	17.1429	120	0.7575	0.5023	0.7575	0.8703
No log	17.4286	122	0.7570	0.5037	0.7570	0.8701
No log	17.7143	124	0.7506	0.5197	0.7506	0.8664
No log	18.0	126	0.7326	0.5111	0.7326	0.8559
No log	18.2857	128	0.7173	0.5373	0.7173	0.8469
No log	18.5714	130	0.7100	0.5121	0.7100	0.8426
No log	18.8571	132	0.6833	0.5569	0.6833	0.8266
No log	19.1429	134	0.6983	0.5266	0.6983	0.8357
No log	19.4286	136	0.7207	0.5181	0.7207	0.8490
No log	19.7143	138	0.7106	0.4960	0.7106	0.8430
No log	20.0	140	0.6855	0.5569	0.6855	0.8280
No log	20.2857	142	0.6864	0.5754	0.6864	0.8285
No log	20.5714	144	0.7150	0.5582	0.7150	0.8456
No log	20.8571	146	0.7525	0.5277	0.7525	0.8675
No log	21.1429	148	0.7623	0.4848	0.7623	0.8731
No log	21.4286	150	0.7447	0.4968	0.7447	0.8630
No log	21.7143	152	0.7371	0.5303	0.7371	0.8585
No log	22.0	154	0.7513	0.5540	0.7513	0.8668
No log	22.2857	156	0.7740	0.4952	0.7740	0.8798
No log	22.5714	158	0.7741	0.4911	0.7741	0.8798
No log	22.8571	160	0.7459	0.5764	0.7459	0.8637
No log	23.1429	162	0.7469	0.5345	0.7469	0.8642
No log	23.4286	164	0.7546	0.5272	0.7546	0.8687
No log	23.7143	166	0.7783	0.5056	0.7783	0.8822
No log	24.0	168	0.7860	0.4764	0.7860	0.8865
No log	24.2857	170	0.7762	0.5108	0.7762	0.8810
No log	24.5714	172	0.7766	0.5309	0.7766	0.8812
No log	24.8571	174	0.7817	0.5256	0.7817	0.8841
No log	25.1429	176	0.7891	0.5282	0.7891	0.8883
No log	25.4286	178	0.7962	0.5351	0.7962	0.8923
No log	25.7143	180	0.7661	0.5487	0.7661	0.8753
No log	26.0	182	0.7448	0.5696	0.7448	0.8630
No log	26.2857	184	0.7402	0.5333	0.7402	0.8603
No log	26.5714	186	0.7097	0.5395	0.7097	0.8425
No log	26.8571	188	0.7060	0.5395	0.7060	0.8403
No log	27.1429	190	0.7449	0.5614	0.7449	0.8630
No log	27.4286	192	0.8113	0.4836	0.8113	0.9007
No log	27.7143	194	0.8677	0.4882	0.8677	0.9315
No log	28.0	196	0.8850	0.4904	0.8850	0.9408
No log	28.2857	198	0.8638	0.4855	0.8638	0.9294
No log	28.5714	200	0.8382	0.4602	0.8382	0.9156
No log	28.8571	202	0.8266	0.4915	0.8266	0.9091
No log	29.1429	204	0.8038	0.5076	0.8038	0.8966
No log	29.4286	206	0.8100	0.5115	0.8100	0.9000
No log	29.7143	208	0.8159	0.4775	0.8159	0.9033
No log	30.0	210	0.8290	0.4641	0.8290	0.9105
No log	30.2857	212	0.8355	0.4789	0.8355	0.9141
No log	30.5714	214	0.8661	0.5035	0.8661	0.9306
No log	30.8571	216	0.8719	0.4700	0.8719	0.9337
No log	31.1429	218	0.8535	0.4621	0.8535	0.9238
No log	31.4286	220	0.8185	0.4826	0.8185	0.9047
No log	31.7143	222	0.7599	0.5375	0.7599	0.8717
No log	32.0	224	0.7385	0.5438	0.7385	0.8594
No log	32.2857	226	0.7754	0.5425	0.7754	0.8805
No log	32.5714	228	0.8384	0.5453	0.8384	0.9156
No log	32.8571	230	0.8771	0.5204	0.8771	0.9365
No log	33.1429	232	0.9012	0.5124	0.9012	0.9493
No log	33.4286	234	0.9065	0.5027	0.9065	0.9521
No log	33.7143	236	0.8880	0.5136	0.8880	0.9424
No log	34.0	238	0.8393	0.5142	0.8393	0.9161
No log	34.2857	240	0.8098	0.5104	0.8098	0.8999
No log	34.5714	242	0.8291	0.5090	0.8291	0.9106
No log	34.8571	244	0.8317	0.5090	0.8317	0.9120
No log	35.1429	246	0.8333	0.5248	0.8333	0.9129
No log	35.4286	248	0.8182	0.5125	0.8182	0.9045
No log	35.7143	250	0.8176	0.5075	0.8176	0.9042
No log	36.0	252	0.8325	0.5083	0.8325	0.9124
No log	36.2857	254	0.8504	0.4800	0.8504	0.9222
No log	36.5714	256	0.8540	0.4654	0.8540	0.9241
No log	36.8571	258	0.8336	0.4921	0.8336	0.9130
No log	37.1429	260	0.7908	0.5075	0.7908	0.8893
No log	37.4286	262	0.7674	0.5237	0.7674	0.8760
No log	37.7143	264	0.7585	0.5481	0.7585	0.8709
No log	38.0	266	0.7547	0.5343	0.7547	0.8687
No log	38.2857	268	0.7422	0.5343	0.7422	0.8615
No log	38.5714	270	0.7461	0.5481	0.7461	0.8638
No log	38.8571	272	0.7662	0.5005	0.7662	0.8753
No log	39.1429	274	0.7939	0.4695	0.7939	0.8910
No log	39.4286	276	0.8142	0.4724	0.8142	0.9023
No log	39.7143	278	0.8154	0.4797	0.8154	0.9030
No log	40.0	280	0.8046	0.4781	0.8046	0.8970
No log	40.2857	282	0.7979	0.4445	0.7979	0.8933
No log	40.5714	284	0.8040	0.4546	0.8040	0.8966
No log	40.8571	286	0.8042	0.4698	0.8042	0.8968
No log	41.1429	288	0.7903	0.4445	0.7903	0.8890
No log	41.4286	290	0.7968	0.4693	0.7968	0.8926
No log	41.7143	292	0.8121	0.4803	0.8121	0.9012
No log	42.0	294	0.8114	0.4940	0.8114	0.9008
No log	42.2857	296	0.7963	0.4809	0.7963	0.8924
No log	42.5714	298	0.7849	0.4933	0.7849	0.8860
No log	42.8571	300	0.7852	0.5278	0.7852	0.8861
No log	43.1429	302	0.7814	0.5024	0.7814	0.8840
No log	43.4286	304	0.7913	0.5368	0.7913	0.8895
No log	43.7143	306	0.8086	0.5532	0.8086	0.8992
No log	44.0	308	0.8049	0.5024	0.8049	0.8972
No log	44.2857	310	0.8066	0.5193	0.8066	0.8981
No log	44.5714	312	0.8296	0.5206	0.8296	0.9108
No log	44.8571	314	0.8438	0.5072	0.8438	0.9186
No log	45.1429	316	0.8560	0.4647	0.8560	0.9252
No log	45.4286	318	0.8806	0.4543	0.8806	0.9384
No log	45.7143	320	0.8836	0.4594	0.8836	0.9400
No log	46.0	322	0.8715	0.4546	0.8715	0.9335
No log	46.2857	324	0.8449	0.4698	0.8449	0.9192
No log	46.5714	326	0.8225	0.4972	0.8225	0.9069
No log	46.8571	328	0.8078	0.4781	0.8078	0.8988
No log	47.1429	330	0.8031	0.5127	0.8031	0.8962
No log	47.4286	332	0.8214	0.5311	0.8214	0.9063
No log	47.7143	334	0.8362	0.4889	0.8362	0.9144
No log	48.0	336	0.8386	0.4898	0.8386	0.9157
No log	48.2857	338	0.8297	0.5012	0.8297	0.9109
No log	48.5714	340	0.8364	0.5012	0.8364	0.9145
No log	48.8571	342	0.8536	0.5012	0.8536	0.9239
No log	49.1429	344	0.8750	0.5113	0.8750	0.9354
No log	49.4286	346	0.8846	0.5145	0.8846	0.9405
No log	49.7143	348	0.8774	0.5093	0.8774	0.9367
No log	50.0	350	0.8717	0.5213	0.8717	0.9336
No log	50.2857	352	0.8802	0.5282	0.8802	0.9382
No log	50.5714	354	0.8874	0.4676	0.8874	0.9420
No log	50.8571	356	0.9033	0.4472	0.9033	0.9504
No log	51.1429	358	0.9047	0.4635	0.9047	0.9512
No log	51.4286	360	0.9183	0.4635	0.9183	0.9583
No log	51.7143	362	0.9380	0.4535	0.9380	0.9685
No log	52.0	364	0.9563	0.4590	0.9563	0.9779
No log	52.2857	366	0.9598	0.4560	0.9598	0.9797
No log	52.5714	368	0.9538	0.4441	0.9538	0.9766
No log	52.8571	370	0.9510	0.4439	0.9510	0.9752
No log	53.1429	372	0.9288	0.4454	0.9288	0.9637
No log	53.4286	374	0.9115	0.4405	0.9115	0.9547
No log	53.7143	376	0.9144	0.4521	0.9144	0.9563
No log	54.0	378	0.9254	0.4388	0.9254	0.9620
No log	54.2857	380	0.9404	0.4548	0.9404	0.9698
No log	54.5714	382	0.9577	0.4493	0.9577	0.9786
No log	54.8571	384	0.9680	0.4603	0.9680	0.9839
No log	55.1429	386	0.9722	0.4792	0.9722	0.9860
No log	55.4286	388	0.9762	0.4792	0.9762	0.9880
No log	55.7143	390	0.9744	0.4527	0.9744	0.9871
No log	56.0	392	0.9660	0.4540	0.9660	0.9829
No log	56.2857	394	0.9673	0.4479	0.9673	0.9835
No log	56.5714	396	0.9583	0.4565	0.9583	0.9789
No log	56.8571	398	0.9466	0.4565	0.9466	0.9729
No log	57.1429	400	0.9304	0.4565	0.9304	0.9646
No log	57.4286	402	0.9102	0.4481	0.9102	0.9540
No log	57.7143	404	0.8850	0.4676	0.8850	0.9407
No log	58.0	406	0.8727	0.5156	0.8727	0.9342
No log	58.2857	408	0.8632	0.5150	0.8632	0.9291
No log	58.5714	410	0.8684	0.5069	0.8684	0.9319
No log	58.8571	412	0.8598	0.5170	0.8598	0.9273
No log	59.1429	414	0.8556	0.5089	0.8556	0.9250
No log	59.4286	416	0.8674	0.5023	0.8674	0.9313
No log	59.7143	418	0.8785	0.4748	0.8785	0.9373
No log	60.0	420	0.8872	0.4641	0.8872	0.9419
No log	60.2857	422	0.9056	0.4548	0.9056	0.9516
No log	60.5714	424	0.9063	0.4452	0.9063	0.9520
No log	60.8571	426	0.9121	0.4643	0.9121	0.9551
No log	61.1429	428	0.9256	0.4456	0.9256	0.9621
No log	61.4286	430	0.9315	0.4577	0.9315	0.9652
No log	61.7143	432	0.9178	0.4521	0.9178	0.9580
No log	62.0	434	0.8980	0.4882	0.8980	0.9476
No log	62.2857	436	0.8614	0.5133	0.8614	0.9281
No log	62.5714	438	0.8369	0.5328	0.8369	0.9148
No log	62.8571	440	0.8393	0.5262	0.8393	0.9161
No log	63.1429	442	0.8640	0.5035	0.8640	0.9295
No log	63.4286	444	0.8844	0.4748	0.8844	0.9404
No log	63.7143	446	0.9017	0.4689	0.9017	0.9496
No log	64.0	448	0.9109	0.4557	0.9109	0.9544
No log	64.2857	450	0.9228	0.4737	0.9228	0.9606
No log	64.5714	452	0.9238	0.4537	0.9238	0.9612
No log	64.8571	454	0.9286	0.4732	0.9286	0.9636
No log	65.1429	456	0.9333	0.4750	0.9333	0.9661
No log	65.4286	458	0.9157	0.4797	0.9157	0.9569
No log	65.7143	460	0.8907	0.4925	0.8907	0.9438
No log	66.0	462	0.8607	0.4704	0.8607	0.9278
No log	66.2857	464	0.8416	0.5049	0.8416	0.9174
No log	66.5714	466	0.8370	0.5080	0.8370	0.9149
No log	66.8571	468	0.8448	0.5112	0.8448	0.9191
No log	67.1429	470	0.8667	0.5027	0.8667	0.9309
No log	67.4286	472	0.8981	0.4689	0.8981	0.9477
No log	67.7143	474	0.9233	0.4587	0.9233	0.9609
No log	68.0	476	0.9440	0.4686	0.9440	0.9716
No log	68.2857	478	0.9572	0.4954	0.9572	0.9784
No log	68.5714	480	0.9621	0.4775	0.9621	0.9809
No log	68.8571	482	0.9516	0.4542	0.9516	0.9755
No log	69.1429	484	0.9305	0.4490	0.9305	0.9646
No log	69.4286	486	0.9155	0.4658	0.9155	0.9568
No log	69.7143	488	0.9092	0.4646	0.9092	0.9535
No log	70.0	490	0.8891	0.4834	0.8891	0.9429
No log	70.2857	492	0.8750	0.4962	0.8750	0.9354
No log	70.5714	494	0.8648	0.5328	0.8648	0.9300
No log	70.8571	496	0.8709	0.5184	0.8709	0.9332
No log	71.1429	498	0.8809	0.5184	0.8809	0.9386
0.5111	71.4286	500	0.8796	0.5145	0.8796	0.9378
0.5111	71.7143	502	0.8917	0.4795	0.8917	0.9443
0.5111	72.0	504	0.9133	0.4737	0.9133	0.9556
0.5111	72.2857	506	0.9348	0.4828	0.9348	0.9669
0.5111	72.5714	508	0.9513	0.4828	0.9513	0.9754
0.5111	72.8571	510	0.9546	0.4713	0.9546	0.9770

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.2.0
• Tokenizers 0.19.1