ArabicNewSplits7_FineTuningAraBERT_run1_AugV5_k7_task7_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: 0.6962
• Qwk: 0.4496
• Mse: 0.6962
• Rmse: 0.8344

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	2.5233	-0.0924	2.5233	1.5885
No log	0.2	4	1.3088	-0.0141	1.3088	1.1440
No log	0.3	6	0.8683	-0.0841	0.8683	0.9318
No log	0.4	8	0.7302	0.1232	0.7302	0.8545
No log	0.5	10	0.7162	0.1321	0.7162	0.8463
No log	0.6	12	0.6981	0.0851	0.6981	0.8355
No log	0.7	14	0.7524	0.2558	0.7524	0.8674
No log	0.8	16	0.8060	0.3173	0.8060	0.8978
No log	0.9	18	0.8405	0.2841	0.8405	0.9168
No log	1.0	20	0.7620	0.1372	0.7620	0.8729
No log	1.1	22	0.7405	-0.0500	0.7405	0.8605
No log	1.2	24	0.7865	0.1313	0.7865	0.8869
No log	1.3	26	0.7876	0.3099	0.7876	0.8875
No log	1.4	28	0.7940	0.1550	0.7940	0.8911
No log	1.5	30	0.7659	0.1007	0.7659	0.8751
No log	1.6	32	0.7374	0.1508	0.7374	0.8587
No log	1.7	34	0.6885	0.0717	0.6885	0.8298
No log	1.8	36	0.6536	0.1942	0.6536	0.8084
No log	1.9	38	0.6287	0.3019	0.6287	0.7929
No log	2.0	40	0.6474	0.2522	0.6474	0.8046
No log	2.1	42	0.6845	0.2464	0.6845	0.8273
No log	2.2	44	0.6942	0.2526	0.6942	0.8332
No log	2.3	46	0.6201	0.1903	0.6201	0.7875
No log	2.4	48	0.7380	0.3699	0.7380	0.8591
No log	2.5	50	0.8357	0.3409	0.8357	0.9142
No log	2.6	52	0.7688	0.2574	0.7688	0.8768
No log	2.7	54	0.6042	0.3274	0.6042	0.7773
No log	2.8	56	0.5931	0.3151	0.5931	0.7701
No log	2.9	58	0.5894	0.3499	0.5894	0.7677
No log	3.0	60	0.5806	0.3105	0.5806	0.7620
No log	3.1	62	0.5450	0.3151	0.5450	0.7382
No log	3.2	64	0.5750	0.4330	0.5750	0.7583
No log	3.3	66	0.6647	0.3799	0.6647	0.8153
No log	3.4	68	0.6143	0.3843	0.6143	0.7838
No log	3.5	70	0.5592	0.4795	0.5592	0.7478
No log	3.6	72	0.5599	0.5056	0.5599	0.7483
No log	3.7	74	0.6522	0.3544	0.6522	0.8076
No log	3.8	76	0.5816	0.3813	0.5816	0.7626
No log	3.9	78	0.5553	0.3945	0.5553	0.7452
No log	4.0	80	0.5704	0.4044	0.5704	0.7552
No log	4.1	82	0.6438	0.3662	0.6438	0.8024
No log	4.2	84	0.6417	0.2843	0.6417	0.8011
No log	4.3	86	0.5697	0.4322	0.5697	0.7548
No log	4.4	88	0.5366	0.4908	0.5366	0.7326
No log	4.5	90	0.5236	0.5373	0.5236	0.7236
No log	4.6	92	0.4963	0.5283	0.4963	0.7045
No log	4.7	94	0.4920	0.4938	0.4920	0.7014
No log	4.8	96	0.5321	0.4315	0.5321	0.7295
No log	4.9	98	0.7985	0.4542	0.7985	0.8936
No log	5.0	100	0.8853	0.4305	0.8853	0.9409
No log	5.1	102	0.6889	0.4646	0.6889	0.8300
No log	5.2	104	0.6207	0.4371	0.6207	0.7878
No log	5.3	106	0.5951	0.4473	0.5951	0.7714
No log	5.4	108	0.5120	0.5815	0.5120	0.7155
No log	5.5	110	0.5111	0.6377	0.5111	0.7149
No log	5.6	112	0.5174	0.5177	0.5174	0.7193
No log	5.7	114	0.6225	0.4550	0.6225	0.7890
No log	5.8	116	0.7525	0.4667	0.7525	0.8675
No log	5.9	118	0.6666	0.4197	0.6666	0.8165
No log	6.0	120	0.5900	0.5015	0.5900	0.7681
No log	6.1	122	0.5245	0.4937	0.5245	0.7242
No log	6.2	124	0.5192	0.5289	0.5192	0.7205
No log	6.3	126	0.5478	0.5357	0.5478	0.7401
No log	6.4	128	0.6098	0.4933	0.6098	0.7809
No log	6.5	130	0.7100	0.5175	0.7100	0.8426
No log	6.6	132	0.5341	0.5024	0.5341	0.7308
No log	6.7	134	0.4604	0.5555	0.4604	0.6785
No log	6.8	136	0.4604	0.5555	0.4604	0.6785
No log	6.9	138	0.4609	0.5846	0.4609	0.6789
No log	7.0	140	0.4756	0.6377	0.4756	0.6896
No log	7.1	142	0.5106	0.6053	0.5106	0.7146
No log	7.2	144	0.5324	0.5332	0.5324	0.7296
No log	7.3	146	0.5182	0.6492	0.5182	0.7199
No log	7.4	148	0.5026	0.5593	0.5026	0.7089
No log	7.5	150	0.5060	0.5549	0.5060	0.7113
No log	7.6	152	0.5096	0.4934	0.5096	0.7139
No log	7.7	154	0.5177	0.5114	0.5177	0.7195
No log	7.8	156	0.5368	0.5307	0.5368	0.7327
No log	7.9	158	0.5412	0.5307	0.5412	0.7357
No log	8.0	160	0.5862	0.3737	0.5862	0.7656
No log	8.1	162	0.6631	0.4502	0.6631	0.8143
No log	8.2	164	0.5987	0.4212	0.5987	0.7738
No log	8.3	166	0.5711	0.4816	0.5711	0.7557
No log	8.4	168	0.5785	0.5379	0.5785	0.7606
No log	8.5	170	0.5902	0.5110	0.5902	0.7683
No log	8.6	172	0.5815	0.6039	0.5815	0.7626
No log	8.7	174	0.6255	0.4724	0.6255	0.7909
No log	8.8	176	0.7438	0.4158	0.7438	0.8624
No log	8.9	178	0.6936	0.4837	0.6936	0.8328
No log	9.0	180	0.6191	0.5324	0.6191	0.7868
No log	9.1	182	0.5963	0.5321	0.5963	0.7722
No log	9.2	184	0.5853	0.4801	0.5853	0.7650
No log	9.3	186	0.6210	0.4788	0.6210	0.7880
No log	9.4	188	0.7345	0.4351	0.7345	0.8570
No log	9.5	190	0.7294	0.3582	0.7294	0.8540
No log	9.6	192	0.6062	0.5115	0.6062	0.7786
No log	9.7	194	0.6178	0.5607	0.6178	0.7860
No log	9.8	196	0.6530	0.4892	0.6530	0.8081
No log	9.9	198	0.5944	0.5319	0.5944	0.7710
No log	10.0	200	0.5693	0.4816	0.5693	0.7545
No log	10.1	202	0.6074	0.3471	0.6074	0.7793
No log	10.2	204	0.6098	0.3545	0.6098	0.7809
No log	10.3	206	0.5779	0.4267	0.5779	0.7602
No log	10.4	208	0.5717	0.4338	0.5717	0.7561
No log	10.5	210	0.5746	0.4229	0.5746	0.7580
No log	10.6	212	0.6091	0.3737	0.6091	0.7804
No log	10.7	214	0.6584	0.3918	0.6584	0.8114
No log	10.8	216	0.7031	0.3869	0.7031	0.8385
No log	10.9	218	0.7002	0.3869	0.7002	0.8368
No log	11.0	220	0.6590	0.3963	0.6590	0.8118
No log	11.1	222	0.6143	0.3918	0.6143	0.7838
No log	11.2	224	0.5873	0.4059	0.5873	0.7664
No log	11.3	226	0.5654	0.5034	0.5654	0.7519
No log	11.4	228	0.5635	0.5269	0.5635	0.7506
No log	11.5	230	0.5802	0.4655	0.5802	0.7617
No log	11.6	232	0.5705	0.3781	0.5705	0.7553
No log	11.7	234	0.5984	0.3763	0.5984	0.7736
No log	11.8	236	0.7083	0.3843	0.7083	0.8416
No log	11.9	238	0.8045	0.4275	0.8045	0.8970
No log	12.0	240	0.7908	0.4275	0.7908	0.8892
No log	12.1	242	0.7043	0.4197	0.7043	0.8392
No log	12.2	244	0.6151	0.4315	0.6151	0.7843
No log	12.3	246	0.5950	0.4315	0.5950	0.7713
No log	12.4	248	0.5840	0.4562	0.5840	0.7642
No log	12.5	250	0.5886	0.4997	0.5886	0.7672
No log	12.6	252	0.6075	0.4371	0.6075	0.7794
No log	12.7	254	0.5664	0.5123	0.5664	0.7526
No log	12.8	256	0.5907	0.4997	0.5907	0.7686
No log	12.9	258	0.6856	0.4088	0.6856	0.8280
No log	13.0	260	0.6791	0.4629	0.6791	0.8241
No log	13.1	262	0.6010	0.3879	0.6010	0.7752
No log	13.2	264	0.6177	0.3865	0.6177	0.7860
No log	13.3	266	0.6933	0.4036	0.6933	0.8326
No log	13.4	268	0.6658	0.4606	0.6658	0.8160
No log	13.5	270	0.5858	0.4644	0.5858	0.7654
No log	13.6	272	0.5599	0.4644	0.5599	0.7483
No log	13.7	274	0.5469	0.4234	0.5469	0.7395
No log	13.8	276	0.5521	0.4473	0.5521	0.7430
No log	13.9	278	0.5563	0.4473	0.5563	0.7459
No log	14.0	280	0.5591	0.5016	0.5591	0.7478
No log	14.1	282	0.5563	0.4769	0.5563	0.7458
No log	14.2	284	0.5736	0.4769	0.5736	0.7574
No log	14.3	286	0.5345	0.5016	0.5345	0.7311
No log	14.4	288	0.4918	0.4661	0.4918	0.7013
No log	14.5	290	0.4977	0.5692	0.4977	0.7055
No log	14.6	292	0.5081	0.5570	0.5081	0.7128
No log	14.7	294	0.5161	0.5853	0.5161	0.7184
No log	14.8	296	0.5267	0.5389	0.5267	0.7257
No log	14.9	298	0.5310	0.5548	0.5310	0.7287
No log	15.0	300	0.6032	0.5794	0.6032	0.7767
No log	15.1	302	0.6586	0.5614	0.6586	0.8115
No log	15.2	304	0.6029	0.5657	0.6029	0.7765
No log	15.3	306	0.5463	0.4914	0.5463	0.7391
No log	15.4	308	0.6419	0.4272	0.6419	0.8012
No log	15.5	310	0.7648	0.4400	0.7648	0.8745
No log	15.6	312	0.7493	0.4738	0.7493	0.8656
No log	15.7	314	0.6584	0.4829	0.6584	0.8114
No log	15.8	316	0.5769	0.4260	0.5769	0.7595
No log	15.9	318	0.5665	0.5304	0.5665	0.7526
No log	16.0	320	0.5683	0.5742	0.5683	0.7538
No log	16.1	322	0.5999	0.4644	0.5999	0.7745
No log	16.2	324	0.6988	0.4805	0.6988	0.8360
No log	16.3	326	0.6457	0.4755	0.6457	0.8036
No log	16.4	328	0.5635	0.5034	0.5635	0.7507
No log	16.5	330	0.5294	0.5159	0.5294	0.7276
No log	16.6	332	0.5253	0.5625	0.5253	0.7248
No log	16.7	334	0.5321	0.5071	0.5321	0.7294
No log	16.8	336	0.5237	0.4314	0.5237	0.7237
No log	16.9	338	0.5478	0.4788	0.5478	0.7401
No log	17.0	340	0.6101	0.4112	0.6101	0.7811
No log	17.1	342	0.6753	0.4721	0.6753	0.8218
No log	17.2	344	0.6219	0.4606	0.6219	0.7886
No log	17.3	346	0.5288	0.4948	0.5288	0.7272
No log	17.4	348	0.5149	0.4809	0.5149	0.7175
No log	17.5	350	0.5302	0.4898	0.5302	0.7282
No log	17.6	352	0.5273	0.5703	0.5273	0.7261
No log	17.7	354	0.5464	0.4966	0.5464	0.7392
No log	17.8	356	0.5632	0.4864	0.5632	0.7505
No log	17.9	358	0.5519	0.4864	0.5519	0.7429
No log	18.0	360	0.5252	0.5345	0.5252	0.7247
No log	18.1	362	0.5089	0.5076	0.5089	0.7134
No log	18.2	364	0.5074	0.5455	0.5074	0.7123
No log	18.3	366	0.5541	0.4920	0.5541	0.7444
No log	18.4	368	0.6561	0.4898	0.6561	0.8100
No log	18.5	370	0.6951	0.4824	0.6951	0.8337
No log	18.6	372	0.6549	0.4700	0.6549	0.8093
No log	18.7	374	0.5713	0.4423	0.5713	0.7558
No log	18.8	376	0.5337	0.5034	0.5337	0.7305
No log	18.9	378	0.5198	0.4808	0.5198	0.7210
No log	19.0	380	0.5097	0.4895	0.5097	0.7139
No log	19.1	382	0.5013	0.5056	0.5013	0.7080
No log	19.2	384	0.4962	0.5605	0.4962	0.7044
No log	19.3	386	0.5000	0.4888	0.5000	0.7071
No log	19.4	388	0.5061	0.4100	0.5061	0.7114
No log	19.5	390	0.5151	0.4100	0.5151	0.7177
No log	19.6	392	0.5284	0.4100	0.5284	0.7269
No log	19.7	394	0.5416	0.4352	0.5416	0.7359
No log	19.8	396	0.5218	0.4100	0.5218	0.7223
No log	19.9	398	0.5240	0.4948	0.5240	0.7239
No log	20.0	400	0.5329	0.5015	0.5329	0.7300
No log	20.1	402	0.5200	0.4966	0.5200	0.7211
No log	20.2	404	0.5207	0.4966	0.5207	0.7216
No log	20.3	406	0.5047	0.5379	0.5047	0.7104
No log	20.4	408	0.5090	0.6759	0.5090	0.7135
No log	20.5	410	0.5155	0.6183	0.5155	0.7180
No log	20.6	412	0.5122	0.5860	0.5122	0.7157
No log	20.7	414	0.5172	0.5501	0.5172	0.7191
No log	20.8	416	0.5607	0.4933	0.5607	0.7488
No log	20.9	418	0.6628	0.4223	0.6628	0.8141
No log	21.0	420	0.6975	0.4648	0.6975	0.8352
No log	21.1	422	0.6470	0.4328	0.6470	0.8044
No log	21.2	424	0.5484	0.3918	0.5484	0.7405
No log	21.3	426	0.5099	0.3996	0.5099	0.7140
No log	21.4	428	0.5035	0.3996	0.5035	0.7095
No log	21.5	430	0.5011	0.4724	0.5011	0.7079
No log	21.6	432	0.5110	0.5098	0.5110	0.7148
No log	21.7	434	0.5579	0.4836	0.5579	0.7469
No log	21.8	436	0.5738	0.4836	0.5738	0.7575
No log	21.9	438	0.5323	0.5081	0.5323	0.7296
No log	22.0	440	0.5230	0.4845	0.5230	0.7232
No log	22.1	442	0.5087	0.4867	0.5087	0.7132
No log	22.2	444	0.4991	0.4983	0.4991	0.7065
No log	22.3	446	0.5084	0.4547	0.5084	0.7130
No log	22.4	448	0.5221	0.4618	0.5221	0.7226
No log	22.5	450	0.5429	0.5223	0.5429	0.7368
No log	22.6	452	0.5832	0.5117	0.5832	0.7637
No log	22.7	454	0.6080	0.4909	0.6080	0.7797
No log	22.8	456	0.5846	0.5524	0.5846	0.7646
No log	22.9	458	0.5400	0.5457	0.5400	0.7349
No log	23.0	460	0.5123	0.5816	0.5123	0.7157
No log	23.1	462	0.4965	0.5738	0.4965	0.7046
No log	23.2	464	0.4945	0.5609	0.4945	0.7032
No log	23.3	466	0.5050	0.5362	0.5050	0.7106
No log	23.4	468	0.5654	0.4522	0.5654	0.7520
No log	23.5	470	0.7035	0.4650	0.7035	0.8387
No log	23.6	472	0.7139	0.4844	0.7139	0.8449
No log	23.7	474	0.5945	0.5310	0.5945	0.7710
No log	23.8	476	0.4889	0.5379	0.4889	0.6992
No log	23.9	478	0.4731	0.5672	0.4731	0.6878
No log	24.0	480	0.4896	0.5999	0.4896	0.6997
No log	24.1	482	0.4753	0.5861	0.4753	0.6895
No log	24.2	484	0.4636	0.5488	0.4636	0.6809
No log	24.3	486	0.4777	0.6201	0.4777	0.6911
No log	24.4	488	0.4890	0.5801	0.4890	0.6993
No log	24.5	490	0.4872	0.5455	0.4872	0.6980
No log	24.6	492	0.4750	0.6096	0.4750	0.6892
No log	24.7	494	0.4702	0.6215	0.4702	0.6857
No log	24.8	496	0.4980	0.5999	0.4980	0.7057
No log	24.9	498	0.4986	0.5999	0.4986	0.7061
0.302	25.0	500	0.4828	0.6068	0.4828	0.6949
0.302	25.1	502	0.4861	0.6439	0.4861	0.6972
0.302	25.2	504	0.4988	0.6228	0.4988	0.7063
0.302	25.3	506	0.4871	0.5941	0.4871	0.6979
0.302	25.4	508	0.4866	0.6477	0.4866	0.6975
0.302	25.5	510	0.4984	0.5918	0.4984	0.7060
0.302	25.6	512	0.5056	0.6013	0.5056	0.7111
0.302	25.7	514	0.4884	0.6370	0.4884	0.6989
0.302	25.8	516	0.4920	0.5738	0.4920	0.7014
0.302	25.9	518	0.5374	0.4721	0.5374	0.7330
0.302	26.0	520	0.6619	0.4496	0.6619	0.8136
0.302	26.1	522	0.7290	0.4467	0.7290	0.8538
0.302	26.2	524	0.6962	0.4496	0.6962	0.8344

Framework versions

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