ArabicNewSplits6_WithDuplicationsForScore5_FineTuningAraBERT_run2_AugV5_k9_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: 0.7353
• Qwk: 0.7250
• Mse: 0.7353
• Rmse: 0.8575

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	2.2629	0.0282	2.2629	1.5043
No log	0.1111	4	1.5387	0.1908	1.5387	1.2404
No log	0.1667	6	1.4391	0.1408	1.4391	1.1996
No log	0.2222	8	1.4470	0.3137	1.4470	1.2029
No log	0.2778	10	1.5807	0.3289	1.5807	1.2572
No log	0.3333	12	1.5766	0.3234	1.5766	1.2556
No log	0.3889	14	1.4009	0.2856	1.4009	1.1836
No log	0.4444	16	1.7726	0.3092	1.7726	1.3314
No log	0.5	18	1.8968	0.3158	1.8968	1.3773
No log	0.5556	20	1.4786	0.3320	1.4786	1.2160
No log	0.6111	22	1.2333	0.3510	1.2333	1.1105
No log	0.6667	24	1.1760	0.3400	1.1760	1.0844
No log	0.7222	26	1.0971	0.4272	1.0971	1.0474
No log	0.7778	28	1.1111	0.4471	1.1111	1.0541
No log	0.8333	30	1.2128	0.4546	1.2128	1.1013
No log	0.8889	32	1.1300	0.5025	1.1300	1.0630
No log	0.9444	34	0.9383	0.5046	0.9383	0.9686
No log	1.0	36	0.9532	0.5189	0.9532	0.9763
No log	1.0556	38	0.9607	0.4286	0.9607	0.9802
No log	1.1111	40	0.8920	0.5295	0.8920	0.9445
No log	1.1667	42	0.8757	0.5011	0.8757	0.9358
No log	1.2222	44	0.9139	0.4830	0.9139	0.9560
No log	1.2778	46	1.0608	0.4521	1.0608	1.0299
No log	1.3333	48	1.2790	0.4517	1.2790	1.1309
No log	1.3889	50	1.2892	0.4516	1.2892	1.1354
No log	1.4444	52	1.4174	0.4435	1.4174	1.1905
No log	1.5	54	1.2796	0.5183	1.2796	1.1312
No log	1.5556	56	0.9019	0.6274	0.9019	0.9497
No log	1.6111	58	0.7637	0.6530	0.7637	0.8739
No log	1.6667	60	0.7287	0.7101	0.7287	0.8536
No log	1.7222	62	0.7322	0.6916	0.7322	0.8557
No log	1.7778	64	0.8274	0.6565	0.8274	0.9096
No log	1.8333	66	1.0230	0.6280	1.0230	1.0114
No log	1.8889	68	1.0284	0.6308	1.0284	1.0141
No log	1.9444	70	0.8097	0.6865	0.8097	0.8998
No log	2.0	72	0.7037	0.7093	0.7037	0.8389
No log	2.0556	74	0.7350	0.6522	0.7350	0.8573
No log	2.1111	76	0.7344	0.6605	0.7344	0.8570
No log	2.1667	78	0.8342	0.6247	0.8342	0.9133
No log	2.2222	80	1.1963	0.5964	1.1963	1.0938
No log	2.2778	82	1.5385	0.5154	1.5385	1.2404
No log	2.3333	84	1.4819	0.5188	1.4819	1.2173
No log	2.3889	86	1.0822	0.6060	1.0822	1.0403
No log	2.4444	88	0.7341	0.7171	0.7341	0.8568
No log	2.5	90	0.6610	0.7012	0.6610	0.8130
No log	2.5556	92	0.6666	0.7108	0.6666	0.8164
No log	2.6111	94	0.7403	0.7544	0.7403	0.8604
No log	2.6667	96	0.8587	0.7056	0.8587	0.9267
No log	2.7222	98	0.8255	0.7455	0.8255	0.9085
No log	2.7778	100	0.7459	0.7656	0.7459	0.8636
No log	2.8333	102	0.7573	0.7656	0.7573	0.8702
No log	2.8889	104	0.7978	0.7431	0.7978	0.8932
No log	2.9444	106	0.8292	0.7361	0.8292	0.9106
No log	3.0	108	0.7842	0.7433	0.7842	0.8856
No log	3.0556	110	0.8130	0.7380	0.8130	0.9017
No log	3.1111	112	0.9054	0.6583	0.9054	0.9515
No log	3.1667	114	0.8456	0.7044	0.8456	0.9195
No log	3.2222	116	0.7778	0.7338	0.7778	0.8819
No log	3.2778	118	0.7704	0.7349	0.7704	0.8777
No log	3.3333	120	0.8601	0.7306	0.8601	0.9274
No log	3.3889	122	0.8977	0.7253	0.8977	0.9475
No log	3.4444	124	0.9501	0.7158	0.9501	0.9747
No log	3.5	126	0.9692	0.6974	0.9692	0.9845
No log	3.5556	128	0.8083	0.7226	0.8083	0.8991
No log	3.6111	130	0.7678	0.7147	0.7678	0.8762
No log	3.6667	132	0.7916	0.6980	0.7916	0.8897
No log	3.7222	134	0.7311	0.7262	0.7311	0.8550
No log	3.7778	136	0.6792	0.7081	0.6792	0.8242
No log	3.8333	138	0.6834	0.7058	0.6834	0.8267
No log	3.8889	140	0.7566	0.7170	0.7566	0.8698
No log	3.9444	142	0.9119	0.7051	0.9119	0.9550
No log	4.0	144	1.1755	0.5629	1.1755	1.0842
No log	4.0556	146	1.1737	0.5737	1.1737	1.0834
No log	4.1111	148	0.9804	0.6540	0.9804	0.9901
No log	4.1667	150	0.7411	0.7344	0.7411	0.8609
No log	4.2222	152	0.6668	0.7331	0.6668	0.8166
No log	4.2778	154	0.6706	0.7284	0.6706	0.8189
No log	4.3333	156	0.7141	0.7351	0.7141	0.8451
No log	4.3889	158	0.7881	0.7413	0.7881	0.8878
No log	4.4444	160	0.7780	0.7419	0.7780	0.8820
No log	4.5	162	0.7713	0.7328	0.7713	0.8783
No log	4.5556	164	0.7675	0.7215	0.7675	0.8761
No log	4.6111	166	0.7292	0.7200	0.7292	0.8539
No log	4.6667	168	0.6536	0.7514	0.6536	0.8084
No log	4.7222	170	0.6330	0.7405	0.6330	0.7956
No log	4.7778	172	0.6210	0.7259	0.6210	0.7880
No log	4.8333	174	0.6251	0.7259	0.6251	0.7907
No log	4.8889	176	0.6135	0.7068	0.6135	0.7833
No log	4.9444	178	0.6251	0.6901	0.6251	0.7907
No log	5.0	180	0.6655	0.6892	0.6655	0.8158
No log	5.0556	182	0.6477	0.7022	0.6477	0.8048
No log	5.1111	184	0.6225	0.7010	0.6225	0.7890
No log	5.1667	186	0.7006	0.7515	0.7006	0.8370
No log	5.2222	188	0.8073	0.7268	0.8073	0.8985
No log	5.2778	190	0.8311	0.7065	0.8311	0.9116
No log	5.3333	192	0.7844	0.7187	0.7844	0.8857
No log	5.3889	194	0.7027	0.7179	0.7027	0.8383
No log	5.4444	196	0.6512	0.7275	0.6512	0.8070
No log	5.5	198	0.6466	0.7275	0.6466	0.8041
No log	5.5556	200	0.6696	0.7268	0.6696	0.8183
No log	5.6111	202	0.7504	0.7527	0.7504	0.8663
No log	5.6667	204	0.8065	0.7049	0.8065	0.8981
No log	5.7222	206	0.7874	0.7537	0.7874	0.8874
No log	5.7778	208	0.7224	0.7432	0.7224	0.8500
No log	5.8333	210	0.6789	0.7413	0.6789	0.8239
No log	5.8889	212	0.6609	0.7413	0.6609	0.8129
No log	5.9444	214	0.6686	0.7413	0.6686	0.8177
No log	6.0	216	0.6883	0.7413	0.6883	0.8296
No log	6.0556	218	0.7500	0.7265	0.7500	0.8660
No log	6.1111	220	0.7440	0.7265	0.7440	0.8626
No log	6.1667	222	0.7286	0.7145	0.7286	0.8536
No log	6.2222	224	0.7208	0.7035	0.7208	0.8490
No log	6.2778	226	0.6917	0.6995	0.6917	0.8317
No log	6.3333	228	0.6775	0.6976	0.6775	0.8231
No log	6.3889	230	0.6743	0.7095	0.6743	0.8211
No log	6.4444	232	0.7025	0.7105	0.7025	0.8381
No log	6.5	234	0.7845	0.7279	0.7845	0.8857
No log	6.5556	236	0.8199	0.7039	0.8199	0.9055
No log	6.6111	238	0.8299	0.6947	0.8299	0.9110
No log	6.6667	240	0.8503	0.6898	0.8503	0.9221
No log	6.7222	242	0.8127	0.7097	0.8127	0.9015
No log	6.7778	244	0.7888	0.7036	0.7888	0.8882
No log	6.8333	246	0.7755	0.6952	0.7755	0.8806
No log	6.8889	248	0.8004	0.6749	0.8004	0.8946
No log	6.9444	250	0.8360	0.6902	0.8360	0.9143
No log	7.0	252	0.8148	0.6965	0.8148	0.9027
No log	7.0556	254	0.7808	0.6786	0.7808	0.8837
No log	7.1111	256	0.7366	0.7198	0.7366	0.8583
No log	7.1667	258	0.7346	0.7161	0.7346	0.8571
No log	7.2222	260	0.7506	0.7279	0.7506	0.8663
No log	7.2778	262	0.7719	0.7258	0.7719	0.8786
No log	7.3333	264	0.7849	0.7258	0.7849	0.8860
No log	7.3889	266	0.7657	0.7243	0.7657	0.8750
No log	7.4444	268	0.7486	0.7329	0.7486	0.8652
No log	7.5	270	0.7367	0.7293	0.7367	0.8583
No log	7.5556	272	0.7435	0.7293	0.7435	0.8623
No log	7.6111	274	0.7812	0.7036	0.7812	0.8838
No log	7.6667	276	0.8014	0.7036	0.8014	0.8952
No log	7.7222	278	0.8003	0.6913	0.8003	0.8946
No log	7.7778	280	0.7893	0.6913	0.7893	0.8884
No log	7.8333	282	0.7913	0.6870	0.7913	0.8896
No log	7.8889	284	0.7970	0.6936	0.7970	0.8927
No log	7.9444	286	0.7811	0.6988	0.7811	0.8838
No log	8.0	288	0.7676	0.6988	0.7676	0.8761
No log	8.0556	290	0.7570	0.6902	0.7570	0.8700
No log	8.1111	292	0.7599	0.6894	0.7599	0.8717
No log	8.1667	294	0.7552	0.6988	0.7552	0.8690
No log	8.2222	296	0.7272	0.7124	0.7272	0.8528
No log	8.2778	298	0.7028	0.7115	0.7028	0.8383
No log	8.3333	300	0.7047	0.7364	0.7047	0.8395
No log	8.3889	302	0.7055	0.7364	0.7055	0.8399
No log	8.4444	304	0.7255	0.7242	0.7255	0.8518
No log	8.5	306	0.7587	0.7250	0.7587	0.8710
No log	8.5556	308	0.8076	0.6942	0.8076	0.8987
No log	8.6111	310	0.8530	0.6797	0.8530	0.9236
No log	8.6667	312	0.8567	0.6797	0.8567	0.9256
No log	8.7222	314	0.8256	0.6882	0.8256	0.9086
No log	8.7778	316	0.7754	0.7158	0.7754	0.8806
No log	8.8333	318	0.7283	0.7192	0.7283	0.8534
No log	8.8889	320	0.7012	0.7343	0.7012	0.8374
No log	8.9444	322	0.6848	0.7470	0.6848	0.8276
No log	9.0	324	0.6842	0.7470	0.6842	0.8271
No log	9.0556	326	0.6950	0.7343	0.6950	0.8336
No log	9.1111	328	0.6999	0.7343	0.6999	0.8366
No log	9.1667	330	0.7006	0.7343	0.7006	0.8370
No log	9.2222	332	0.7100	0.7321	0.7100	0.8426
No log	9.2778	334	0.7264	0.7314	0.7264	0.8523
No log	9.3333	336	0.7376	0.7250	0.7376	0.8589
No log	9.3889	338	0.7428	0.7250	0.7428	0.8618
No log	9.4444	340	0.7416	0.7250	0.7416	0.8611
No log	9.5	342	0.7403	0.7250	0.7403	0.8604
No log	9.5556	344	0.7385	0.7250	0.7385	0.8593
No log	9.6111	346	0.7365	0.7250	0.7365	0.8582
No log	9.6667	348	0.7378	0.7250	0.7378	0.8589
No log	9.7222	350	0.7380	0.7250	0.7380	0.8590
No log	9.7778	352	0.7370	0.7250	0.7370	0.8585
No log	9.8333	354	0.7357	0.7250	0.7357	0.8578
No log	9.8889	356	0.7344	0.7250	0.7344	0.8570
No log	9.9444	358	0.7346	0.7250	0.7346	0.8571
No log	10.0	360	0.7353	0.7250	0.7353	0.8575

Framework versions

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