ArabicNewSplits4_FineTuningAraBERT_run2_AugV5_k11_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: 0.9423
• Qwk: 0.6442
• Mse: 0.9423
• Rmse: 0.9707

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	0.0571	2	2.2613	0.0523	2.2613	1.5038
No log	0.1143	4	1.4823	0.1930	1.4823	1.2175
No log	0.1714	6	1.3714	0.1850	1.3714	1.1711
No log	0.2286	8	1.7533	0.2871	1.7533	1.3241
No log	0.2857	10	1.8268	0.2930	1.8268	1.3516
No log	0.3429	12	1.7654	0.2457	1.7654	1.3287
No log	0.4	14	1.6829	0.2639	1.6829	1.2973
No log	0.4571	16	1.5186	0.1252	1.5186	1.2323
No log	0.5143	18	1.4247	0.1463	1.4247	1.1936
No log	0.5714	20	1.4285	0.2051	1.4285	1.1952
No log	0.6286	22	1.4625	0.3382	1.4625	1.2093
No log	0.6857	24	1.5788	0.3335	1.5788	1.2565
No log	0.7429	26	1.4941	0.3667	1.4941	1.2223
No log	0.8	28	1.4718	0.3757	1.4718	1.2132
No log	0.8571	30	1.4543	0.3569	1.4543	1.2059
No log	0.9143	32	1.2947	0.3953	1.2947	1.1379
No log	0.9714	34	1.2395	0.4159	1.2395	1.1134
No log	1.0286	36	1.1823	0.4159	1.1823	1.0873
No log	1.0857	38	1.2797	0.3760	1.2797	1.1312
No log	1.1429	40	1.5718	0.3467	1.5718	1.2537
No log	1.2	42	1.7424	0.3076	1.7424	1.3200
No log	1.2571	44	1.5517	0.4074	1.5517	1.2457
No log	1.3143	46	1.3810	0.4257	1.3810	1.1752
No log	1.3714	48	1.5132	0.4208	1.5132	1.2301
No log	1.4286	50	2.0913	0.3913	2.0913	1.4461
No log	1.4857	52	2.7850	0.2563	2.7850	1.6688
No log	1.5429	54	2.8945	0.2761	2.8945	1.7013
No log	1.6	56	2.6216	0.3538	2.6216	1.6191
No log	1.6571	58	2.4072	0.3682	2.4072	1.5515
No log	1.7143	60	2.2917	0.3759	2.2917	1.5138
No log	1.7714	62	1.7459	0.4535	1.7459	1.3213
No log	1.8286	64	1.2283	0.4491	1.2283	1.1083
No log	1.8857	66	1.0939	0.4926	1.0939	1.0459
No log	1.9429	68	1.1786	0.4444	1.1786	1.0856
No log	2.0	70	1.4709	0.4511	1.4709	1.2128
No log	2.0571	72	1.8561	0.3754	1.8561	1.3624
No log	2.1143	74	1.7856	0.4232	1.7856	1.3363
No log	2.1714	76	1.3625	0.4743	1.3625	1.1672
No log	2.2286	78	1.0166	0.5185	1.0166	1.0083
No log	2.2857	80	0.8521	0.5807	0.8521	0.9231
No log	2.3429	82	0.9247	0.5621	0.9247	0.9616
No log	2.4	84	1.1259	0.5625	1.1259	1.0611
No log	2.4571	86	1.2362	0.5651	1.2362	1.1118
No log	2.5143	88	1.4094	0.5131	1.4094	1.1872
No log	2.5714	90	1.3525	0.5034	1.3525	1.1630
No log	2.6286	92	1.1099	0.5291	1.1099	1.0535
No log	2.6857	94	1.0203	0.5459	1.0203	1.0101
No log	2.7429	96	0.9839	0.5747	0.9839	0.9919
No log	2.8	98	0.9155	0.6172	0.9155	0.9568
No log	2.8571	100	1.0943	0.5990	1.0943	1.0461
No log	2.9143	102	1.4264	0.5485	1.4264	1.1943
No log	2.9714	104	1.4533	0.5500	1.4533	1.2055
No log	3.0286	106	1.0997	0.6125	1.0997	1.0487
No log	3.0857	108	0.7818	0.6795	0.7818	0.8842
No log	3.1429	110	0.7248	0.7137	0.7248	0.8514
No log	3.2	112	0.7377	0.7039	0.7377	0.8589
No log	3.2571	114	0.7889	0.6560	0.7889	0.8882
No log	3.3143	116	0.7680	0.6512	0.7680	0.8764
No log	3.3714	118	0.8247	0.6259	0.8247	0.9081
No log	3.4286	120	0.7956	0.6466	0.7956	0.8920
No log	3.4857	122	0.6709	0.7151	0.6709	0.8191
No log	3.5429	124	0.6479	0.7227	0.6479	0.8049
No log	3.6	126	0.6656	0.7245	0.6656	0.8159
No log	3.6571	128	0.8678	0.6662	0.8678	0.9315
No log	3.7143	130	1.1656	0.5778	1.1656	1.0796
No log	3.7714	132	1.1726	0.5901	1.1726	1.0829
No log	3.8286	134	0.9517	0.6561	0.9517	0.9755
No log	3.8857	136	0.7412	0.6943	0.7412	0.8609
No log	3.9429	138	0.7021	0.6951	0.7021	0.8379
No log	4.0	140	0.7817	0.6588	0.7817	0.8842
No log	4.0571	142	0.9607	0.6163	0.9607	0.9802
No log	4.1143	144	1.1329	0.5859	1.1329	1.0644
No log	4.1714	146	1.0735	0.5811	1.0735	1.0361
No log	4.2286	148	0.9011	0.6093	0.9011	0.9493
No log	4.2857	150	0.8629	0.6160	0.8629	0.9289
No log	4.3429	152	0.8591	0.6195	0.8591	0.9269
No log	4.4	154	0.9240	0.6143	0.9240	0.9613
No log	4.4571	156	0.8859	0.6089	0.8859	0.9412
No log	4.5143	158	0.8574	0.6052	0.8574	0.9259
No log	4.5714	160	0.8224	0.6182	0.8224	0.9069
No log	4.6286	162	0.9382	0.6441	0.9382	0.9686
No log	4.6857	164	1.1595	0.6025	1.1595	1.0768
No log	4.7429	166	1.1837	0.6070	1.1837	1.0880
No log	4.8	168	1.0235	0.6198	1.0235	1.0117
No log	4.8571	170	0.9430	0.6561	0.9430	0.9711
No log	4.9143	172	0.9306	0.6603	0.9306	0.9647
No log	4.9714	174	0.9915	0.6389	0.9915	0.9957
No log	5.0286	176	1.0534	0.6155	1.0534	1.0263
No log	5.0857	178	1.0586	0.6267	1.0586	1.0289
No log	5.1429	180	0.9928	0.6458	0.9928	0.9964
No log	5.2	182	0.9221	0.6919	0.9221	0.9603
No log	5.2571	184	0.8098	0.7085	0.8098	0.8999
No log	5.3143	186	0.6812	0.7409	0.6812	0.8254
No log	5.3714	188	0.6528	0.7240	0.6528	0.8080
No log	5.4286	190	0.6493	0.7194	0.6493	0.8058
No log	5.4857	192	0.6796	0.7303	0.6796	0.8244
No log	5.5429	194	0.7257	0.7289	0.7257	0.8519
No log	5.6	196	0.6820	0.7317	0.6820	0.8258
No log	5.6571	198	0.6571	0.7450	0.6571	0.8106
No log	5.7143	200	0.6655	0.7367	0.6655	0.8158
No log	5.7714	202	0.7377	0.7380	0.7377	0.8589
No log	5.8286	204	0.8289	0.7030	0.8289	0.9105
No log	5.8857	206	0.9229	0.6545	0.9229	0.9607
No log	5.9429	208	0.9618	0.6441	0.9618	0.9807
No log	6.0	210	0.8576	0.6839	0.8576	0.9261
No log	6.0571	212	0.7249	0.7289	0.7249	0.8514
No log	6.1143	214	0.6726	0.7548	0.6726	0.8201
No log	6.1714	216	0.6603	0.7598	0.6603	0.8126
No log	6.2286	218	0.6700	0.7631	0.6700	0.8185
No log	6.2857	220	0.7347	0.7226	0.7347	0.8571
No log	6.3429	222	0.8958	0.6821	0.8958	0.9465
No log	6.4	224	1.0157	0.6168	1.0157	1.0078
No log	6.4571	226	1.0224	0.6226	1.0224	1.0111
No log	6.5143	228	0.9328	0.6472	0.9328	0.9658
No log	6.5714	230	0.9217	0.6385	0.9217	0.9601
No log	6.6286	232	0.8964	0.6492	0.8964	0.9468
No log	6.6857	234	0.9368	0.6427	0.9368	0.9679
No log	6.7429	236	0.9830	0.6446	0.9830	0.9915
No log	6.8	238	1.0070	0.6341	1.0070	1.0035
No log	6.8571	240	1.0163	0.6239	1.0163	1.0081
No log	6.9143	242	1.0237	0.6181	1.0237	1.0118
No log	6.9714	244	0.9205	0.6571	0.9205	0.9594
No log	7.0286	246	0.8112	0.7184	0.8112	0.9007
No log	7.0857	248	0.7535	0.7154	0.7535	0.8680
No log	7.1429	250	0.6965	0.7410	0.6965	0.8346
No log	7.2	252	0.6964	0.7435	0.6964	0.8345
No log	7.2571	254	0.7367	0.7132	0.7367	0.8583
No log	7.3143	256	0.7805	0.7262	0.7805	0.8835
No log	7.3714	258	0.8382	0.7103	0.8382	0.9156
No log	7.4286	260	0.8238	0.7030	0.8238	0.9076
No log	7.4857	262	0.8191	0.7030	0.8191	0.9050
No log	7.5429	264	0.7967	0.7030	0.7967	0.8926
No log	7.6	266	0.7529	0.7105	0.7529	0.8677
No log	7.6571	268	0.7446	0.7105	0.7446	0.8629
No log	7.7143	270	0.7629	0.7068	0.7629	0.8735
No log	7.7714	272	0.7853	0.7030	0.7853	0.8862
No log	7.8286	274	0.8091	0.7030	0.8091	0.8995
No log	7.8857	276	0.8124	0.7008	0.8124	0.9013
No log	7.9429	278	0.8160	0.7008	0.8160	0.9033
No log	8.0	280	0.8515	0.6839	0.8515	0.9227
No log	8.0571	282	0.8716	0.6730	0.8716	0.9336
No log	8.1143	284	0.8973	0.6623	0.8973	0.9473
No log	8.1714	286	0.9528	0.6455	0.9528	0.9761
No log	8.2286	288	0.9493	0.6433	0.9493	0.9743
No log	8.2857	290	0.9445	0.6494	0.9445	0.9718
No log	8.3429	292	0.9246	0.6547	0.9246	0.9615
No log	8.4	294	0.8917	0.6503	0.8917	0.9443
No log	8.4571	296	0.8607	0.6519	0.8607	0.9278
No log	8.5143	298	0.8667	0.6503	0.8667	0.9310
No log	8.5714	300	0.8829	0.6492	0.8829	0.9396
No log	8.6286	302	0.8820	0.6359	0.8820	0.9392
No log	8.6857	304	0.8988	0.6406	0.8988	0.9480
No log	8.7429	306	0.9245	0.6419	0.9245	0.9615
No log	8.8	308	0.9512	0.6491	0.9512	0.9753
No log	8.8571	310	0.9754	0.6491	0.9754	0.9876
No log	8.9143	312	0.9674	0.6479	0.9674	0.9836
No log	8.9714	314	0.9545	0.6479	0.9545	0.9770
No log	9.0286	316	0.9321	0.6506	0.9321	0.9654
No log	9.0857	318	0.8929	0.6547	0.8929	0.9449
No log	9.1429	320	0.8658	0.6563	0.8658	0.9305
No log	9.2	322	0.8625	0.6623	0.8625	0.9287
No log	9.2571	324	0.8765	0.6509	0.8765	0.9362
No log	9.3143	326	0.8976	0.6509	0.8976	0.9474
No log	9.3714	328	0.9104	0.6577	0.9104	0.9541
No log	9.4286	330	0.9248	0.6577	0.9248	0.9617
No log	9.4857	332	0.9324	0.6537	0.9324	0.9656
No log	9.5429	334	0.9349	0.6537	0.9349	0.9669
No log	9.6	336	0.9390	0.6537	0.9390	0.9690
No log	9.6571	338	0.9415	0.6537	0.9415	0.9703
No log	9.7143	340	0.9457	0.6537	0.9457	0.9725
No log	9.7714	342	0.9460	0.6537	0.9460	0.9726
No log	9.8286	344	0.9441	0.6527	0.9441	0.9716
No log	9.8857	346	0.9437	0.6527	0.9437	0.9715
No log	9.9429	348	0.9430	0.6442	0.9430	0.9711
No log	10.0	350	0.9423	0.6442	0.9423	0.9707

Framework versions

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