ArabicNewSplits4_WithDuplicationsForScore5_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: 0.6211
• Qwk: 0.7562
• Mse: 0.6211
• Rmse: 0.7881

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	0.0526	2	2.3263	0.0334	2.3263	1.5252
No log	0.1053	4	1.4987	0.1837	1.4987	1.2242
No log	0.1579	6	1.2826	0.2284	1.2826	1.1325
No log	0.2105	8	1.3391	0.3276	1.3391	1.1572
No log	0.2632	10	1.6474	0.3091	1.6474	1.2835
No log	0.3158	12	1.9054	0.2775	1.9054	1.3804
No log	0.3684	14	1.8793	0.2977	1.8793	1.3709
No log	0.4211	16	1.4974	0.3375	1.4974	1.2237
No log	0.4737	18	1.2295	0.3777	1.2295	1.1088
No log	0.5263	20	1.1815	0.3799	1.1815	1.0870
No log	0.5789	22	1.1041	0.4408	1.1041	1.0507
No log	0.6316	24	1.1576	0.4468	1.1576	1.0759
No log	0.6842	26	1.5883	0.4011	1.5883	1.2603
No log	0.7368	28	1.3649	0.4472	1.3649	1.1683
No log	0.7895	30	1.0425	0.4731	1.0425	1.0210
No log	0.8421	32	0.9607	0.4841	0.9607	0.9802
No log	0.8947	34	0.9643	0.5585	0.9643	0.9820
No log	0.9474	36	0.9150	0.6067	0.9150	0.9565
No log	1.0	38	0.8125	0.6222	0.8125	0.9014
No log	1.0526	40	0.7118	0.6770	0.7118	0.8437
No log	1.1053	42	0.6700	0.7003	0.6700	0.8186
No log	1.1579	44	0.6954	0.7200	0.6954	0.8339
No log	1.2105	46	0.7825	0.7090	0.7825	0.8846
No log	1.2632	48	1.1681	0.6150	1.1681	1.0808
No log	1.3158	50	1.2824	0.6078	1.2824	1.1324
No log	1.3684	52	0.9736	0.6959	0.9736	0.9867
No log	1.4211	54	0.8009	0.7193	0.8009	0.8950
No log	1.4737	56	0.7144	0.7409	0.7144	0.8452
No log	1.5263	58	0.7312	0.7447	0.7312	0.8551
No log	1.5789	60	0.8618	0.7219	0.8618	0.9283
No log	1.6316	62	0.7828	0.7529	0.7828	0.8848
No log	1.6842	64	0.7099	0.7342	0.7099	0.8426
No log	1.7368	66	0.6357	0.7393	0.6357	0.7973
No log	1.7895	68	0.5472	0.7579	0.5472	0.7397
No log	1.8421	70	0.5470	0.7565	0.5470	0.7396
No log	1.8947	72	0.5710	0.7392	0.5710	0.7556
No log	1.9474	74	0.5719	0.7471	0.5719	0.7563
No log	2.0	76	0.6306	0.7443	0.6306	0.7941
No log	2.0526	78	0.6293	0.7329	0.6293	0.7933
No log	2.1053	80	0.5666	0.7220	0.5666	0.7528
No log	2.1579	82	0.5744	0.7328	0.5744	0.7579
No log	2.2105	84	0.5667	0.7380	0.5667	0.7528
No log	2.2632	86	0.6780	0.7384	0.6780	0.8234
No log	2.3158	88	0.7186	0.7387	0.7186	0.8477
No log	2.3684	90	0.5608	0.7672	0.5608	0.7489
No log	2.4211	92	0.5143	0.7560	0.5143	0.7172
No log	2.4737	94	0.5409	0.6937	0.5409	0.7355
No log	2.5263	96	0.5536	0.6940	0.5536	0.7441
No log	2.5789	98	0.5154	0.7324	0.5154	0.7179
No log	2.6316	100	0.6036	0.7441	0.6036	0.7769
No log	2.6842	102	0.6025	0.7420	0.6025	0.7762
No log	2.7368	104	0.5443	0.7467	0.5443	0.7378
No log	2.7895	106	0.5215	0.7455	0.5215	0.7221
No log	2.8421	108	0.5293	0.7196	0.5293	0.7275
No log	2.8947	110	0.5328	0.7563	0.5328	0.7300
No log	2.9474	112	0.6961	0.7565	0.6961	0.8343
No log	3.0	114	0.7091	0.7571	0.7091	0.8421
No log	3.0526	116	0.5721	0.7492	0.5721	0.7563
No log	3.1053	118	0.5357	0.7414	0.5357	0.7319
No log	3.1579	120	0.5532	0.7470	0.5532	0.7438
No log	3.2105	122	0.5317	0.7600	0.5317	0.7292
No log	3.2632	124	0.6396	0.7544	0.6396	0.7998
No log	3.3158	126	0.6754	0.7544	0.6754	0.8219
No log	3.3684	128	0.6386	0.7606	0.6386	0.7991
No log	3.4211	130	0.5943	0.7501	0.5943	0.7709
No log	3.4737	132	0.5928	0.7602	0.5928	0.7699
No log	3.5263	134	0.6078	0.7555	0.6078	0.7796
No log	3.5789	136	0.6811	0.7421	0.6811	0.8253
No log	3.6316	138	0.7377	0.7489	0.7377	0.8589
No log	3.6842	140	0.6942	0.7423	0.6942	0.8332
No log	3.7368	142	0.5856	0.7523	0.5856	0.7652
No log	3.7895	144	0.5547	0.7193	0.5547	0.7448
No log	3.8421	146	0.5571	0.7306	0.5571	0.7464
No log	3.8947	148	0.6038	0.7648	0.6038	0.7770
No log	3.9474	150	0.7595	0.7451	0.7595	0.8715
No log	4.0	152	0.9235	0.6861	0.9235	0.9610
No log	4.0526	154	0.8409	0.7156	0.8409	0.9170
No log	4.1053	156	0.6294	0.7609	0.6294	0.7934
No log	4.1579	158	0.5487	0.7330	0.5487	0.7407
No log	4.2105	160	0.5505	0.7283	0.5505	0.7420
No log	4.2632	162	0.5702	0.7493	0.5702	0.7551
No log	4.3158	164	0.7539	0.7310	0.7539	0.8683
No log	4.3684	166	0.8971	0.6855	0.8971	0.9471
No log	4.4211	168	0.8506	0.6916	0.8506	0.9223
No log	4.4737	170	0.7555	0.7102	0.7555	0.8692
No log	4.5263	172	0.7705	0.6919	0.7705	0.8778
No log	4.5789	174	0.7262	0.7194	0.7262	0.8522
No log	4.6316	176	0.7201	0.7175	0.7201	0.8486
No log	4.6842	178	0.7611	0.7275	0.7611	0.8724
No log	4.7368	180	0.7181	0.7558	0.7181	0.8474
No log	4.7895	182	0.6468	0.7674	0.6468	0.8042
No log	4.8421	184	0.6554	0.7560	0.6554	0.8096
No log	4.8947	186	0.7290	0.7580	0.7290	0.8538
No log	4.9474	188	0.8093	0.7374	0.8093	0.8996
No log	5.0	190	0.8148	0.7254	0.8148	0.9026
No log	5.0526	192	0.7294	0.7432	0.7294	0.8540
No log	5.1053	194	0.6324	0.7556	0.6324	0.7952
No log	5.1579	196	0.5922	0.7501	0.5922	0.7695
No log	5.2105	198	0.5790	0.7237	0.5790	0.7609
No log	5.2632	200	0.6035	0.7421	0.6035	0.7769
No log	5.3158	202	0.6886	0.7644	0.6886	0.8298
No log	5.3684	204	0.7987	0.7309	0.7987	0.8937
No log	5.4211	206	0.7948	0.7350	0.7948	0.8915
No log	5.4737	208	0.6834	0.7622	0.6834	0.8267
No log	5.5263	210	0.5776	0.7530	0.5776	0.7600
No log	5.5789	212	0.5629	0.7603	0.5629	0.7503
No log	5.6316	214	0.5705	0.7377	0.5705	0.7553
No log	5.6842	216	0.6268	0.7519	0.6268	0.7917
No log	5.7368	218	0.7811	0.7467	0.7811	0.8838
No log	5.7895	220	0.9244	0.7079	0.9244	0.9614
No log	5.8421	222	0.9315	0.7041	0.9315	0.9651
No log	5.8947	224	0.8378	0.7110	0.8378	0.9153
No log	5.9474	226	0.7049	0.7487	0.7049	0.8396
No log	6.0	228	0.6566	0.7431	0.6566	0.8103
No log	6.0526	230	0.6622	0.7353	0.6622	0.8137
No log	6.1053	232	0.7060	0.7387	0.7060	0.8403
No log	6.1579	234	0.7906	0.7337	0.7906	0.8892
No log	6.2105	236	0.8316	0.6999	0.8316	0.9119
No log	6.2632	238	0.8140	0.7072	0.8140	0.9022
No log	6.3158	240	0.7473	0.7338	0.7473	0.8645
No log	6.3684	242	0.6815	0.7410	0.6815	0.8255
No log	6.4211	244	0.6593	0.7476	0.6593	0.8120
No log	6.4737	246	0.6800	0.7410	0.6800	0.8246
No log	6.5263	248	0.7526	0.7296	0.7526	0.8675
No log	6.5789	250	0.7905	0.7254	0.7905	0.8891
No log	6.6316	252	0.7677	0.7295	0.7677	0.8762
No log	6.6842	254	0.6856	0.7552	0.6856	0.8280
No log	6.7368	256	0.6318	0.7446	0.6318	0.7949
No log	6.7895	258	0.5838	0.7201	0.5838	0.7641
No log	6.8421	260	0.5669	0.7438	0.5669	0.7529
No log	6.8947	262	0.5590	0.7359	0.5590	0.7476
No log	6.9474	264	0.5636	0.7442	0.5636	0.7507
No log	7.0	266	0.5996	0.7422	0.5996	0.7743
No log	7.0526	268	0.6482	0.7637	0.6482	0.8051
No log	7.1053	270	0.6583	0.7590	0.6583	0.8113
No log	7.1579	272	0.6408	0.7562	0.6408	0.8005
No log	7.2105	274	0.6149	0.7605	0.6149	0.7842
No log	7.2632	276	0.5840	0.7627	0.5840	0.7642
No log	7.3158	278	0.5664	0.7586	0.5664	0.7526
No log	7.3684	280	0.5684	0.7644	0.5684	0.7539
No log	7.4211	282	0.5803	0.7449	0.5803	0.7618
No log	7.4737	284	0.5748	0.7449	0.5748	0.7582
No log	7.5263	286	0.5604	0.7474	0.5604	0.7486
No log	7.5789	288	0.5607	0.7401	0.5607	0.7488
No log	7.6316	290	0.5714	0.7414	0.5714	0.7559
No log	7.6842	292	0.5892	0.7570	0.5892	0.7676
No log	7.7368	294	0.5937	0.7570	0.5937	0.7705
No log	7.7895	296	0.5880	0.7570	0.5880	0.7668
No log	7.8421	298	0.5885	0.7528	0.5885	0.7672
No log	7.8947	300	0.6157	0.7637	0.6157	0.7847
No log	7.9474	302	0.6315	0.7645	0.6315	0.7946
No log	8.0	304	0.6369	0.7650	0.6369	0.7980
No log	8.0526	306	0.6378	0.7650	0.6378	0.7986
No log	8.1053	308	0.6100	0.7637	0.6100	0.7810
No log	8.1579	310	0.5819	0.7432	0.5819	0.7628
No log	8.2105	312	0.5642	0.7639	0.5642	0.7511
No log	8.2632	314	0.5663	0.7620	0.5663	0.7525
No log	8.3158	316	0.5759	0.7665	0.5759	0.7589
No log	8.3684	318	0.5976	0.7562	0.5976	0.7731
No log	8.4211	320	0.6165	0.7618	0.6165	0.7852
No log	8.4737	322	0.6298	0.7650	0.6298	0.7936
No log	8.5263	324	0.6210	0.7692	0.6210	0.7880
No log	8.5789	326	0.6018	0.7522	0.6018	0.7757
No log	8.6316	328	0.5805	0.7444	0.5805	0.7619
No log	8.6842	330	0.5715	0.7577	0.5715	0.7560
No log	8.7368	332	0.5764	0.7444	0.5764	0.7592
No log	8.7895	334	0.5933	0.7478	0.5933	0.7702
No log	8.8421	336	0.6120	0.7522	0.6120	0.7823
No log	8.8947	338	0.6246	0.7692	0.6246	0.7903
No log	8.9474	340	0.6291	0.7692	0.6291	0.7931
No log	9.0	342	0.6203	0.7637	0.6203	0.7876
No log	9.0526	344	0.6030	0.7432	0.6030	0.7765
No log	9.1053	346	0.5938	0.7432	0.5938	0.7706
No log	9.1579	348	0.5897	0.7352	0.5897	0.7679
No log	9.2105	350	0.5843	0.7501	0.5843	0.7644
No log	9.2632	352	0.5824	0.7501	0.5824	0.7632
No log	9.3158	354	0.5852	0.7501	0.5852	0.7650
No log	9.3684	356	0.5907	0.7539	0.5907	0.7686
No log	9.4211	358	0.6007	0.7485	0.6007	0.7751
No log	9.4737	360	0.6085	0.7485	0.6085	0.7801
No log	9.5263	362	0.6109	0.7485	0.6109	0.7816
No log	9.5789	364	0.6136	0.7485	0.6136	0.7833
No log	9.6316	366	0.6159	0.7485	0.6159	0.7848
No log	9.6842	368	0.6172	0.7485	0.6172	0.7856
No log	9.7368	370	0.6189	0.7442	0.6189	0.7867
No log	9.7895	372	0.6214	0.7519	0.6214	0.7883
No log	9.8421	374	0.6222	0.7519	0.6222	0.7888
No log	9.8947	376	0.6222	0.7519	0.6222	0.7888
No log	9.9474	378	0.6213	0.7562	0.6213	0.7882
No log	10.0	380	0.6211	0.7562	0.6211	0.7881

Framework versions

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