Arabic_FineTuningAraBERT_AugV4_k1_task2_organization_fold1

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: 0.4088
• Qwk: 0.6197
• Mse: 0.4088
• Rmse: 0.6394

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	0.0769	2	7.9724	0.0	7.9724	2.8236
No log	0.1538	4	4.5770	0.0084	4.5770	2.1394
No log	0.2308	6	2.1854	0.0702	2.1854	1.4783
No log	0.3077	8	0.9244	0.0548	0.9244	0.9614
No log	0.3846	10	0.5648	0.25	0.5648	0.7516
No log	0.4615	12	0.8170	0.3636	0.8170	0.9039
No log	0.5385	14	0.7506	0.3636	0.7506	0.8664
No log	0.6154	16	0.6729	0.0870	0.6729	0.8203
No log	0.6923	18	0.6007	0.0	0.6007	0.7751
No log	0.7692	20	0.5089	0.0870	0.5089	0.7134
No log	0.8462	22	0.5149	0.0870	0.5149	0.7176
No log	0.9231	24	0.4900	0.4643	0.4900	0.7000
No log	1.0	26	0.4944	0.4211	0.4944	0.7031
No log	1.0769	28	0.4775	0.2800	0.4775	0.6910
No log	1.1538	30	0.4824	0.2800	0.4824	0.6946
No log	1.2308	32	0.5038	0.2041	0.5038	0.7098
No log	1.3077	34	0.5545	0.2759	0.5545	0.7447
No log	1.3846	36	0.5299	0.3333	0.5299	0.7280
No log	1.4615	38	0.5030	0.3774	0.5030	0.7093
No log	1.5385	40	0.5043	0.2373	0.5043	0.7102
No log	1.6154	42	0.5165	0.4	0.5165	0.7187
No log	1.6923	44	0.5916	0.2258	0.5916	0.7692
No log	1.7692	46	0.4308	0.5091	0.4308	0.6563
No log	1.8462	48	0.4714	0.3636	0.4714	0.6866
No log	1.9231	50	0.6663	0.3377	0.6663	0.8163
No log	2.0	52	0.6408	0.3846	0.6408	0.8005
No log	2.0769	54	0.6052	0.3544	0.6052	0.7779
No log	2.1538	56	0.4888	0.4474	0.4888	0.6991
No log	2.2308	58	0.4736	0.5424	0.4736	0.6882
No log	2.3077	60	0.6512	0.2154	0.6512	0.8070
No log	2.3846	62	0.9111	0.2192	0.9111	0.9545
No log	2.4615	64	0.7838	0.2703	0.7838	0.8853
No log	2.5385	66	0.4120	0.6129	0.4120	0.6419
No log	2.6154	68	0.4146	0.4590	0.4146	0.6439
No log	2.6923	70	0.4066	0.4375	0.4066	0.6377
No log	2.7692	72	0.3524	0.5588	0.3524	0.5937
No log	2.8462	74	0.3917	0.6038	0.3917	0.6259
No log	2.9231	76	0.3998	0.6038	0.3998	0.6323
No log	3.0	78	0.4081	0.5091	0.4081	0.6388
No log	3.0769	80	0.3648	0.7188	0.3648	0.6040
No log	3.1538	82	0.3684	0.3438	0.3684	0.6070
No log	3.2308	84	0.4884	0.3810	0.4884	0.6988
No log	3.3077	86	0.4728	0.4375	0.4728	0.6876
No log	3.3846	88	0.3942	0.3390	0.3942	0.6278
No log	3.4615	90	0.3594	0.4194	0.3594	0.5995
No log	3.5385	92	0.3732	0.7188	0.3732	0.6109
No log	3.6154	94	0.4123	0.5424	0.4123	0.6421
No log	3.6923	96	0.3830	0.6	0.3830	0.6189
No log	3.7692	98	0.3890	0.5574	0.3890	0.6237
No log	3.8462	100	0.4050	0.5455	0.4050	0.6364
No log	3.9231	102	0.4219	0.5352	0.4219	0.6496
No log	4.0	104	0.5210	0.4706	0.5210	0.7218
No log	4.0769	106	0.7005	0.2222	0.7005	0.8370
No log	4.1538	108	0.7702	0.2683	0.7702	0.8776
No log	4.2308	110	0.6816	0.5714	0.6816	0.8256
No log	4.3077	112	0.4483	0.5823	0.4483	0.6696
No log	4.3846	114	0.3995	0.7	0.3995	0.6321
No log	4.4615	116	0.3951	0.6197	0.3951	0.6286
No log	4.5385	118	0.4024	0.6471	0.4024	0.6344
No log	4.6154	120	0.3942	0.6667	0.3942	0.6278
No log	4.6923	122	0.3701	0.6471	0.3701	0.6084
No log	4.7692	124	0.3329	0.6866	0.3329	0.5770
No log	4.8462	126	0.3226	0.7	0.3226	0.5680
No log	4.9231	128	0.3296	0.7429	0.3296	0.5741
No log	5.0	130	0.4173	0.5227	0.4173	0.6460
No log	5.0769	132	0.4421	0.5517	0.4421	0.6649
No log	5.1538	134	0.4711	0.5517	0.4711	0.6864
No log	5.2308	136	0.4923	0.5517	0.4923	0.7016
No log	5.3077	138	0.4188	0.5517	0.4188	0.6471
No log	5.3846	140	0.3109	0.7429	0.3109	0.5576
No log	5.4615	142	0.3172	0.6769	0.3172	0.5632
No log	5.5385	144	0.3309	0.7	0.3309	0.5753
No log	5.6154	146	0.3343	0.6364	0.3343	0.5782
No log	5.6923	148	0.3423	0.7042	0.3423	0.5850
No log	5.7692	150	0.3808	0.4211	0.3808	0.6171
No log	5.8462	152	0.4603	0.4211	0.4603	0.6784
No log	5.9231	154	0.4738	0.4375	0.4738	0.6883
No log	6.0	156	0.4739	0.4375	0.4739	0.6884
No log	6.0769	158	0.4111	0.4828	0.4111	0.6411
No log	6.1538	160	0.3760	0.6866	0.3760	0.6132
No log	6.2308	162	0.4762	0.4444	0.4762	0.6900
No log	6.3077	164	0.5298	0.475	0.5298	0.7279
No log	6.3846	166	0.5390	0.5063	0.5390	0.7342
No log	6.4615	168	0.5231	0.4615	0.5231	0.7233
No log	6.5385	170	0.4079	0.5301	0.4079	0.6387
No log	6.6154	172	0.3338	0.7692	0.3338	0.5778
No log	6.6923	174	0.3769	0.6182	0.3769	0.6139
No log	6.7692	176	0.3832	0.6182	0.3832	0.6191
No log	6.8462	178	0.3525	0.7	0.3525	0.5937
No log	6.9231	180	0.3502	0.6769	0.3502	0.5918
No log	7.0	182	0.3784	0.4923	0.3784	0.6152
No log	7.0769	184	0.4163	0.4857	0.4163	0.6452
No log	7.1538	186	0.4731	0.4304	0.4731	0.6878
No log	7.2308	188	0.4963	0.4304	0.4963	0.7045
No log	7.3077	190	0.4676	0.4304	0.4676	0.6838
No log	7.3846	192	0.4422	0.475	0.4422	0.6650
No log	7.4615	194	0.4262	0.48	0.4262	0.6528
No log	7.5385	196	0.4146	0.4857	0.4146	0.6439
No log	7.6154	198	0.4133	0.6197	0.4133	0.6429
No log	7.6923	200	0.4193	0.6364	0.4193	0.6476
No log	7.7692	202	0.4188	0.6364	0.4188	0.6472
No log	7.8462	204	0.4102	0.6364	0.4102	0.6405
No log	7.9231	206	0.4028	0.6364	0.4028	0.6347
No log	8.0	208	0.4042	0.6571	0.4042	0.6358
No log	8.0769	210	0.4114	0.7	0.4114	0.6414
No log	8.1538	212	0.4106	0.7	0.4106	0.6407
No log	8.2308	214	0.4091	0.7	0.4091	0.6396
No log	8.3077	216	0.4025	0.7	0.4025	0.6344
No log	8.3846	218	0.3984	0.7	0.3984	0.6312
No log	8.4615	220	0.3920	0.6667	0.3920	0.6261
No log	8.5385	222	0.3826	0.6197	0.3826	0.6185
No log	8.6154	224	0.3836	0.6197	0.3836	0.6194
No log	8.6923	226	0.3863	0.6197	0.3863	0.6215
No log	8.7692	228	0.3922	0.6197	0.3922	0.6263
No log	8.8462	230	0.3978	0.6364	0.3978	0.6307
No log	8.9231	232	0.4006	0.6364	0.4006	0.6329
No log	9.0	234	0.4030	0.6197	0.4030	0.6349
No log	9.0769	236	0.4055	0.6197	0.4055	0.6368
No log	9.1538	238	0.4096	0.6197	0.4096	0.6400
No log	9.2308	240	0.4112	0.6197	0.4112	0.6412
No log	9.3077	242	0.4127	0.6053	0.4127	0.6424
No log	9.3846	244	0.4147	0.6197	0.4147	0.6440
No log	9.4615	246	0.4151	0.6197	0.4151	0.6443
No log	9.5385	248	0.4146	0.6197	0.4146	0.6439
No log	9.6154	250	0.4136	0.6197	0.4136	0.6431
No log	9.6923	252	0.4122	0.6197	0.4122	0.6420
No log	9.7692	254	0.4111	0.6197	0.4111	0.6412
No log	9.8462	256	0.4104	0.6197	0.4104	0.6406
No log	9.9231	258	0.4093	0.6197	0.4093	0.6398
No log	10.0	260	0.4088	0.6197	0.4088	0.6394

Framework versions

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