ArabicNewSplits7_FineTuningAraBERT_run1_AugV5_k7_task5_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: 0.5212
• Qwk: 0.6866
• Mse: 0.5212
• Rmse: 0.7219

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: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	0.1	2	4.0764	0.0130	4.0764	2.0190
No log	0.2	4	2.0564	-0.0252	2.0564	1.4340
No log	0.3	6	1.4209	0.0030	1.4209	1.1920
No log	0.4	8	1.0602	0.2716	1.0602	1.0297
No log	0.5	10	1.2760	0.0374	1.2760	1.1296
No log	0.6	12	1.4109	-0.0627	1.4109	1.1878
No log	0.7	14	1.2724	-0.0477	1.2724	1.1280
No log	0.8	16	1.1484	0.1028	1.1484	1.0716
No log	0.9	18	1.0733	0.2068	1.0733	1.0360
No log	1.0	20	1.0495	0.2236	1.0495	1.0245
No log	1.1	22	1.0321	0.2236	1.0321	1.0159
No log	1.2	24	0.9954	0.2697	0.9954	0.9977
No log	1.3	26	0.9358	0.3243	0.9358	0.9674
No log	1.4	28	0.9000	0.3688	0.9000	0.9487
No log	1.5	30	0.9182	0.4109	0.9182	0.9582
No log	1.6	32	0.8474	0.4585	0.8474	0.9205
No log	1.7	34	0.8921	0.3037	0.8921	0.9445
No log	1.8	36	1.1198	0.2497	1.1198	1.0582
No log	1.9	38	1.5948	-0.1370	1.5948	1.2629
No log	2.0	40	1.5142	-0.1247	1.5142	1.2305
No log	2.1	42	1.0373	0.2467	1.0373	1.0185
No log	2.2	44	0.7922	0.4218	0.7922	0.8900
No log	2.3	46	0.7808	0.4420	0.7808	0.8836
No log	2.4	48	0.7535	0.4568	0.7535	0.8680
No log	2.5	50	0.7503	0.4953	0.7503	0.8662
No log	2.6	52	0.6959	0.5235	0.6959	0.8342
No log	2.7	54	0.7635	0.5487	0.7635	0.8738
No log	2.8	56	1.0131	0.3706	1.0131	1.0065
No log	2.9	58	1.0251	0.4140	1.0251	1.0125
No log	3.0	60	0.9034	0.4681	0.9034	0.9505
No log	3.1	62	0.7010	0.4616	0.7010	0.8373
No log	3.2	64	0.6195	0.6363	0.6195	0.7871
No log	3.3	66	0.6177	0.6207	0.6177	0.7859
No log	3.4	68	0.6122	0.6690	0.6122	0.7824
No log	3.5	70	0.6054	0.6866	0.6054	0.7781
No log	3.6	72	0.5906	0.6869	0.5906	0.7685
No log	3.7	74	0.5826	0.7455	0.5826	0.7633
No log	3.8	76	0.5776	0.7404	0.5776	0.7600
No log	3.9	78	0.6177	0.6644	0.6177	0.7860
No log	4.0	80	0.5713	0.7193	0.5713	0.7559
No log	4.1	82	0.5571	0.7005	0.5571	0.7464
No log	4.2	84	0.5568	0.7399	0.5568	0.7462
No log	4.3	86	0.5813	0.7304	0.5813	0.7624
No log	4.4	88	0.5992	0.7395	0.5992	0.7741
No log	4.5	90	0.5646	0.7177	0.5646	0.7514
No log	4.6	92	0.6011	0.6210	0.6011	0.7753
No log	4.7	94	0.6215	0.6753	0.6215	0.7884
No log	4.8	96	0.5613	0.6751	0.5613	0.7492
No log	4.9	98	0.5922	0.6886	0.5922	0.7695
No log	5.0	100	0.5858	0.7396	0.5858	0.7654
No log	5.1	102	0.5766	0.7246	0.5766	0.7593
No log	5.2	104	0.5887	0.6733	0.5887	0.7673
No log	5.3	106	0.5937	0.6445	0.5937	0.7705
No log	5.4	108	0.6360	0.6296	0.6360	0.7975
No log	5.5	110	0.6987	0.6447	0.6987	0.8359
No log	5.6	112	0.6529	0.6363	0.6529	0.8080
No log	5.7	114	0.5694	0.6883	0.5694	0.7546
No log	5.8	116	0.5639	0.7199	0.5639	0.7509
No log	5.9	118	0.6261	0.6404	0.6261	0.7912
No log	6.0	120	0.6428	0.6507	0.6428	0.8018
No log	6.1	122	0.6771	0.6492	0.6771	0.8229
No log	6.2	124	0.5775	0.6695	0.5775	0.7600
No log	6.3	126	0.5924	0.7061	0.5924	0.7697
No log	6.4	128	0.6309	0.7067	0.6309	0.7943
No log	6.5	130	0.6292	0.6505	0.6292	0.7932
No log	6.6	132	0.6358	0.6064	0.6358	0.7974
No log	6.7	134	0.6041	0.6502	0.6041	0.7772
No log	6.8	136	0.6200	0.6748	0.6200	0.7874
No log	6.9	138	0.6581	0.5964	0.6581	0.8112
No log	7.0	140	0.5902	0.6582	0.5902	0.7682
No log	7.1	142	0.5489	0.7147	0.5489	0.7409
No log	7.2	144	0.5637	0.6919	0.5637	0.7508
No log	7.3	146	0.6461	0.6404	0.6461	0.8038
No log	7.4	148	0.6731	0.6404	0.6731	0.8204
No log	7.5	150	0.5847	0.6543	0.5847	0.7647
No log	7.6	152	0.5600	0.6797	0.5600	0.7484
No log	7.7	154	0.5592	0.6998	0.5592	0.7478
No log	7.8	156	0.5552	0.6674	0.5552	0.7451
No log	7.9	158	0.8022	0.5713	0.8022	0.8957
No log	8.0	160	1.0103	0.5205	1.0103	1.0051
No log	8.1	162	0.9517	0.5771	0.9517	0.9755
No log	8.2	164	0.7013	0.6432	0.7013	0.8374
No log	8.3	166	0.5868	0.6438	0.5868	0.7660
No log	8.4	168	0.5899	0.7203	0.5899	0.7680
No log	8.5	170	0.6215	0.5994	0.6215	0.7883
No log	8.6	172	0.6567	0.6091	0.6567	0.8104
No log	8.7	174	0.6282	0.6256	0.6282	0.7926
No log	8.8	176	0.6265	0.7081	0.6265	0.7915
No log	8.9	178	0.6814	0.5912	0.6814	0.8255
No log	9.0	180	0.6982	0.5912	0.6982	0.8356
No log	9.1	182	0.6812	0.5912	0.6812	0.8253
No log	9.2	184	0.6180	0.6728	0.6180	0.7861
No log	9.3	186	0.5876	0.6262	0.5876	0.7665
No log	9.4	188	0.5700	0.6370	0.5700	0.7550
No log	9.5	190	0.5542	0.6908	0.5542	0.7445
No log	9.6	192	0.5675	0.6647	0.5675	0.7533
No log	9.7	194	0.5550	0.6990	0.5550	0.7450
No log	9.8	196	0.5318	0.7360	0.5318	0.7293
No log	9.9	198	0.5231	0.7272	0.5231	0.7233
No log	10.0	200	0.5389	0.6812	0.5389	0.7341
No log	10.1	202	0.5506	0.6854	0.5506	0.7420
No log	10.2	204	0.5306	0.7033	0.5306	0.7284
No log	10.3	206	0.5337	0.6954	0.5337	0.7306
No log	10.4	208	0.5165	0.7026	0.5165	0.7186
No log	10.5	210	0.5274	0.6240	0.5274	0.7262
No log	10.6	212	0.6999	0.6967	0.6999	0.8366
No log	10.7	214	0.7608	0.6744	0.7608	0.8722
No log	10.8	216	0.6212	0.6780	0.6212	0.7882
No log	10.9	218	0.5086	0.6764	0.5086	0.7131
No log	11.0	220	0.5197	0.7182	0.5197	0.7209
No log	11.1	222	0.5359	0.7384	0.5359	0.7320
No log	11.2	224	0.5119	0.7026	0.5119	0.7155
No log	11.3	226	0.5094	0.7064	0.5094	0.7137
No log	11.4	228	0.5158	0.7178	0.5158	0.7182
No log	11.5	230	0.5417	0.7360	0.5417	0.7360
No log	11.6	232	0.5526	0.7301	0.5526	0.7433
No log	11.7	234	0.5526	0.7450	0.5526	0.7433
No log	11.8	236	0.5401	0.7296	0.5401	0.7349
No log	11.9	238	0.5351	0.6973	0.5351	0.7315
No log	12.0	240	0.5470	0.6843	0.5470	0.7396
No log	12.1	242	0.5602	0.6525	0.5602	0.7485
No log	12.2	244	0.6064	0.6211	0.6064	0.7787
No log	12.3	246	0.7318	0.6069	0.7318	0.8555
No log	12.4	248	0.7613	0.6372	0.7613	0.8725
No log	12.5	250	0.6468	0.6461	0.6468	0.8042
No log	12.6	252	0.5461	0.7061	0.5461	0.7390
No log	12.7	254	0.5360	0.7266	0.5360	0.7321
No log	12.8	256	0.5427	0.7444	0.5427	0.7367
No log	12.9	258	0.5705	0.7191	0.5705	0.7553
No log	13.0	260	0.6115	0.6906	0.6115	0.7820
No log	13.1	262	0.6873	0.6988	0.6873	0.8290
No log	13.2	264	0.6585	0.7161	0.6585	0.8115
No log	13.3	266	0.5807	0.6601	0.5807	0.7620
No log	13.4	268	0.5904	0.6647	0.5904	0.7684
No log	13.5	270	0.5775	0.6703	0.5775	0.7599
No log	13.6	272	0.5673	0.6479	0.5673	0.7532
No log	13.7	274	0.5624	0.6517	0.5624	0.7499
No log	13.8	276	0.5590	0.7059	0.5590	0.7477
No log	13.9	278	0.5658	0.6728	0.5658	0.7522
No log	14.0	280	0.6011	0.5905	0.6011	0.7753
No log	14.1	282	0.6713	0.5816	0.6713	0.8194
No log	14.2	284	0.6832	0.5377	0.6832	0.8265
No log	14.3	286	0.6102	0.5581	0.6102	0.7811
No log	14.4	288	0.5373	0.7025	0.5373	0.7330
No log	14.5	290	0.5285	0.7450	0.5285	0.7270
No log	14.6	292	0.5282	0.7051	0.5282	0.7268
No log	14.7	294	0.5064	0.6940	0.5064	0.7116
No log	14.8	296	0.5871	0.6317	0.5871	0.7662
No log	14.9	298	0.6913	0.5961	0.6913	0.8314
No log	15.0	300	0.6642	0.5770	0.6642	0.8150
No log	15.1	302	0.5629	0.6830	0.5629	0.7503
No log	15.2	304	0.5487	0.6469	0.5487	0.7408
No log	15.3	306	0.6740	0.6170	0.6740	0.8210
No log	15.4	308	0.7100	0.6061	0.7100	0.8426
No log	15.5	310	0.6378	0.6485	0.6378	0.7986
No log	15.6	312	0.5832	0.6297	0.5832	0.7637
No log	15.7	314	0.6753	0.6229	0.6753	0.8217
No log	15.8	316	0.6934	0.6174	0.6934	0.8327
No log	15.9	318	0.6268	0.6175	0.6268	0.7917
No log	16.0	320	0.5584	0.6330	0.5584	0.7473
No log	16.1	322	0.5537	0.6857	0.5537	0.7441
No log	16.2	324	0.6115	0.6491	0.6115	0.7820
No log	16.3	326	0.6405	0.6157	0.6405	0.8003
No log	16.4	328	0.6027	0.6869	0.6027	0.7763
No log	16.5	330	0.5450	0.6425	0.5450	0.7382
No log	16.6	332	0.5426	0.6347	0.5426	0.7366
No log	16.7	334	0.5737	0.6248	0.5737	0.7575
No log	16.8	336	0.5652	0.6838	0.5652	0.7518
No log	16.9	338	0.5345	0.6417	0.5345	0.7311
No log	17.0	340	0.5227	0.6433	0.5227	0.7230
No log	17.1	342	0.5185	0.6610	0.5185	0.7201
No log	17.2	344	0.5114	0.6433	0.5114	0.7151
No log	17.3	346	0.5179	0.6636	0.5179	0.7196
No log	17.4	348	0.5268	0.6526	0.5268	0.7258
No log	17.5	350	0.5198	0.6437	0.5198	0.7210
No log	17.6	352	0.5251	0.6437	0.5251	0.7246
No log	17.7	354	0.5319	0.6566	0.5319	0.7293
No log	17.8	356	0.5782	0.6061	0.5782	0.7604
No log	17.9	358	0.5642	0.6457	0.5642	0.7512
No log	18.0	360	0.5081	0.6708	0.5081	0.7128
No log	18.1	362	0.4927	0.6813	0.4927	0.7019
No log	18.2	364	0.5103	0.6526	0.5103	0.7144
No log	18.3	366	0.5146	0.6526	0.5146	0.7173
No log	18.4	368	0.5141	0.6108	0.5141	0.7170
No log	18.5	370	0.4978	0.6966	0.4978	0.7056
No log	18.6	372	0.5195	0.6694	0.5195	0.7208
No log	18.7	374	0.5799	0.6260	0.5799	0.7615
No log	18.8	376	0.6119	0.6219	0.6119	0.7823
No log	18.9	378	0.5294	0.6967	0.5294	0.7276
No log	19.0	380	0.4645	0.7216	0.4645	0.6816
No log	19.1	382	0.4664	0.7204	0.4664	0.6829
No log	19.2	384	0.5339	0.7220	0.5339	0.7307
No log	19.3	386	0.5528	0.7066	0.5528	0.7435
No log	19.4	388	0.5251	0.6499	0.5251	0.7247
No log	19.5	390	0.5014	0.6894	0.5014	0.7081
No log	19.6	392	0.4968	0.6733	0.4968	0.7048
No log	19.7	394	0.4958	0.6919	0.4958	0.7041
No log	19.8	396	0.5267	0.6943	0.5267	0.7258
No log	19.9	398	0.5433	0.6742	0.5433	0.7371
No log	20.0	400	0.5405	0.7016	0.5405	0.7352
No log	20.1	402	0.5032	0.6993	0.5032	0.7094
No log	20.2	404	0.4909	0.7132	0.4909	0.7007
No log	20.3	406	0.5438	0.6663	0.5438	0.7375
No log	20.4	408	0.5699	0.6455	0.5699	0.7549
No log	20.5	410	0.5415	0.6582	0.5415	0.7359
No log	20.6	412	0.5005	0.6750	0.5005	0.7075
No log	20.7	414	0.4720	0.7245	0.4720	0.6870
No log	20.8	416	0.5004	0.6991	0.5004	0.7074
No log	20.9	418	0.5217	0.6883	0.5217	0.7223
No log	21.0	420	0.4854	0.7267	0.4854	0.6967
No log	21.1	422	0.4630	0.6759	0.4630	0.6804
No log	21.2	424	0.4910	0.6620	0.4910	0.7007
No log	21.3	426	0.5086	0.6663	0.5086	0.7132
No log	21.4	428	0.5246	0.6835	0.5246	0.7243
No log	21.5	430	0.5241	0.6796	0.5241	0.7239
No log	21.6	432	0.5091	0.7067	0.5091	0.7135
No log	21.7	434	0.4979	0.7041	0.4979	0.7056
No log	21.8	436	0.4943	0.6903	0.4943	0.7031
No log	21.9	438	0.4979	0.6869	0.4979	0.7056
No log	22.0	440	0.4941	0.6869	0.4941	0.7029
No log	22.1	442	0.4928	0.7019	0.4928	0.7020
No log	22.2	444	0.4910	0.7405	0.4910	0.7007
No log	22.3	446	0.4944	0.7351	0.4944	0.7032
No log	22.4	448	0.5367	0.7182	0.5367	0.7326
No log	22.5	450	0.5492	0.6833	0.5492	0.7411
No log	22.6	452	0.5258	0.6894	0.5258	0.7251
No log	22.7	454	0.4934	0.6958	0.4934	0.7024
No log	22.8	456	0.4918	0.6813	0.4918	0.7013
No log	22.9	458	0.5011	0.7112	0.5011	0.7079
No log	23.0	460	0.4948	0.6846	0.4948	0.7034
No log	23.1	462	0.5048	0.6683	0.5048	0.7105
No log	23.2	464	0.5271	0.7074	0.5271	0.7260
No log	23.3	466	0.5670	0.7157	0.5670	0.7530
No log	23.4	468	0.5716	0.7071	0.5716	0.7560
No log	23.5	470	0.6096	0.6815	0.6096	0.7808
No log	23.6	472	0.5978	0.7118	0.5978	0.7732
No log	23.7	474	0.5369	0.6970	0.5369	0.7327
No log	23.8	476	0.4943	0.7165	0.4943	0.7031
No log	23.9	478	0.4890	0.6720	0.4890	0.6993
No log	24.0	480	0.5056	0.6736	0.5056	0.7110
No log	24.1	482	0.5203	0.6614	0.5203	0.7213
No log	24.2	484	0.5358	0.6614	0.5358	0.7320
No log	24.3	486	0.5289	0.6614	0.5289	0.7273
No log	24.4	488	0.5152	0.6878	0.5152	0.7178
No log	24.5	490	0.5144	0.6575	0.5144	0.7172
No log	24.6	492	0.5077	0.6519	0.5077	0.7126
No log	24.7	494	0.4939	0.6861	0.4939	0.7028
No log	24.8	496	0.5042	0.6963	0.5042	0.7101
No log	24.9	498	0.5451	0.6906	0.5451	0.7383
0.2684	25.0	500	0.5403	0.6906	0.5403	0.7350
0.2684	25.1	502	0.5105	0.6535	0.5105	0.7145
0.2684	25.2	504	0.5046	0.6680	0.5046	0.7103
0.2684	25.3	506	0.5172	0.6806	0.5172	0.7191
0.2684	25.4	508	0.5179	0.6814	0.5179	0.7196
0.2684	25.5	510	0.5212	0.6866	0.5212	0.7219

Framework versions

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