Arabic_FineTuningAraBERT_AugV5_k5_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: 0.8213
• Qwk: 0.3478
• Mse: 0.8213
• Rmse: 0.9063

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	0.0417	2	5.6903	-0.0325	5.6903	2.3854
No log	0.0833	4	3.0439	0.0097	3.0439	1.7447
No log	0.125	6	1.6444	0.0792	1.6444	1.2824
No log	0.1667	8	1.2140	0.0792	1.2140	1.1018
No log	0.2083	10	1.3429	0.0556	1.3429	1.1588
No log	0.25	12	1.9681	0.1176	1.9681	1.4029
No log	0.2917	14	1.8517	0.1395	1.8517	1.3608
No log	0.3333	16	1.1185	0.0	1.1185	1.0576
No log	0.375	18	0.7108	0.2258	0.7108	0.8431
No log	0.4167	20	0.9270	-0.2187	0.9270	0.9628
No log	0.4583	22	1.2417	0.0	1.2417	1.1143
No log	0.5	24	1.0894	0.0	1.0894	1.0437
No log	0.5417	26	1.0315	0.0	1.0315	1.0156
No log	0.5833	28	1.1757	0.0	1.1757	1.0843
No log	0.625	30	1.0166	0.0	1.0166	1.0082
No log	0.6667	32	0.7839	-0.2581	0.7839	0.8854
No log	0.7083	34	0.7366	-0.1000	0.7366	0.8582
No log	0.75	36	0.6865	-0.1379	0.6865	0.8286
No log	0.7917	38	0.6972	-0.0328	0.6972	0.8350
No log	0.8333	40	0.6690	-0.0345	0.6690	0.8179
No log	0.875	42	0.7167	0.0323	0.7167	0.8466
No log	0.9167	44	0.9196	0.1563	0.9196	0.9590
No log	0.9583	46	1.1560	0.0548	1.1560	1.0752
No log	1.0	48	1.0913	0.0548	1.0913	1.0446
No log	1.0417	50	0.9236	0.1563	0.9236	0.9610
No log	1.0833	52	0.7994	0.1563	0.7994	0.8941
No log	1.125	54	0.6141	0.2373	0.6141	0.7836
No log	1.1667	56	0.5949	0.0	0.5949	0.7713
No log	1.2083	58	0.6815	0.0727	0.6815	0.8255
No log	1.25	60	0.7584	0.1724	0.7584	0.8709
No log	1.2917	62	0.8374	0.0339	0.8374	0.9151
No log	1.3333	64	0.7937	0.1724	0.7937	0.8909
No log	1.375	66	0.7252	0.0	0.7252	0.8516
No log	1.4167	68	0.7192	0.0	0.7192	0.8481
No log	1.4583	70	0.7516	0.0339	0.7516	0.8670
No log	1.5	72	0.7521	0.2373	0.7521	0.8672
No log	1.5417	74	0.8206	0.2373	0.8206	0.9059
No log	1.5833	76	0.7690	0.2373	0.7690	0.8770
No log	1.625	78	0.6770	0.1724	0.6770	0.8228
No log	1.6667	80	0.6725	0.1724	0.6725	0.8200
No log	1.7083	82	0.5802	-0.0385	0.5802	0.7617
No log	1.75	84	0.5699	0.1111	0.5699	0.7549
No log	1.7917	86	0.5120	0.0727	0.5120	0.7156
No log	1.8333	88	0.5166	0.2759	0.5166	0.7187
No log	1.875	90	0.5417	0.3000	0.5417	0.7360
No log	1.9167	92	0.5620	0.1111	0.5620	0.7497
No log	1.9583	94	0.5997	0.1429	0.5997	0.7744
No log	2.0	96	0.6025	0.2759	0.6025	0.7762
No log	2.0417	98	0.6046	0.2759	0.6046	0.7776
No log	2.0833	100	0.5724	0.0727	0.5724	0.7566
No log	2.125	102	0.5858	0.1509	0.5858	0.7654
No log	2.1667	104	0.5898	0.0	0.5898	0.7680
No log	2.2083	106	0.5989	0.3000	0.5989	0.7739
No log	2.25	108	0.6956	0.2727	0.6956	0.8340
No log	2.2917	110	0.7384	0.2727	0.7384	0.8593
No log	2.3333	112	0.6776	0.2286	0.6776	0.8232
No log	2.375	114	0.6382	0.3544	0.6382	0.7989
No log	2.4167	116	0.6003	0.25	0.6003	0.7748
No log	2.4583	118	0.5804	0.1290	0.5804	0.7618
No log	2.5	120	0.5884	0.1493	0.5884	0.7671
No log	2.5417	122	0.6238	0.2105	0.6238	0.7898
No log	2.5833	124	0.6232	0.1750	0.6232	0.7894
No log	2.625	126	0.6371	0.2286	0.6371	0.7982
No log	2.6667	128	0.6782	0.2286	0.6782	0.8235
No log	2.7083	130	0.6724	0.2286	0.6724	0.8200
No log	2.75	132	0.6922	0.1750	0.6922	0.8320
No log	2.7917	134	0.7599	0.2105	0.7599	0.8717
No log	2.8333	136	0.7149	0.1750	0.7149	0.8455
No log	2.875	138	0.7028	0.25	0.7028	0.8383
No log	2.9167	140	0.7311	0.2286	0.7311	0.8551
No log	2.9583	142	0.8013	0.4167	0.8013	0.8951
No log	3.0	144	0.7905	0.2286	0.7905	0.8891
No log	3.0417	146	0.7898	0.1039	0.7898	0.8887
No log	3.0833	148	0.8316	0.1882	0.8316	0.9119
No log	3.125	150	0.8920	0.1039	0.8920	0.9444
No log	3.1667	152	0.9176	0.1951	0.9176	0.9579
No log	3.2083	154	0.9635	0.2921	0.9635	0.9816
No log	3.25	156	1.0628	0.3077	1.0628	1.0309
No log	3.2917	158	1.2908	0.2435	1.2908	1.1361
No log	3.3333	160	1.3074	0.1818	1.3074	1.1434
No log	3.375	162	1.1747	0.1818	1.1747	1.0838
No log	3.4167	164	0.9366	0.3250	0.9366	0.9678
No log	3.4583	166	0.8685	0.2857	0.8685	0.9319
No log	3.5	168	0.9154	0.0741	0.9154	0.9568
No log	3.5417	170	0.8872	0.0741	0.8872	0.9419
No log	3.5833	172	0.8119	0.3704	0.8119	0.9011
No log	3.625	174	0.8667	0.2785	0.8667	0.9310
No log	3.6667	176	0.9618	0.2759	0.9618	0.9807
No log	3.7083	178	0.9690	0.2759	0.9690	0.9844
No log	3.75	180	0.9393	0.2500	0.9393	0.9692
No log	3.7917	182	0.9563	0.2326	0.9563	0.9779
No log	3.8333	184	0.9233	0.3704	0.9233	0.9609
No log	3.875	186	0.8360	0.2895	0.8360	0.9144
No log	3.9167	188	0.9121	0.2653	0.9121	0.9551
No log	3.9583	190	1.1673	0.2222	1.1673	1.0804
No log	4.0	192	1.2667	0.2222	1.2667	1.1255
No log	4.0417	194	1.1286	0.2222	1.1286	1.0624
No log	4.0833	196	0.8915	0.2653	0.8915	0.9442
No log	4.125	198	0.7826	0.3077	0.7826	0.8846
No log	4.1667	200	0.7690	0.2895	0.7690	0.8769
No log	4.2083	202	0.7821	0.3014	0.7821	0.8844
No log	4.25	204	0.8425	0.2667	0.8425	0.9179
No log	4.2917	206	0.8947	0.2667	0.8947	0.9459
No log	4.3333	208	0.8581	0.2921	0.8581	0.9263
No log	4.375	210	0.7865	0.25	0.7865	0.8868
No log	4.4167	212	0.7806	0.25	0.7806	0.8835
No log	4.4583	214	0.7784	0.2921	0.7784	0.8823
No log	4.5	216	0.7462	0.1892	0.7462	0.8638
No log	4.5417	218	0.7201	0.1892	0.7201	0.8486
No log	4.5833	220	0.7319	0.2222	0.7319	0.8555
No log	4.625	222	0.7245	0.1951	0.7245	0.8512
No log	4.6667	224	0.7057	0.1892	0.7057	0.8401
No log	4.7083	226	0.6982	0.2895	0.6982	0.8356
No log	4.75	228	0.7059	0.2895	0.7059	0.8402
No log	4.7917	230	0.7192	0.3377	0.7192	0.8481
No log	4.8333	232	0.7772	0.2667	0.7772	0.8816
No log	4.875	234	0.8381	0.3448	0.8381	0.9155
No log	4.9167	236	0.9149	0.2979	0.9149	0.9565
No log	4.9583	238	0.8673	0.3448	0.8673	0.9313
No log	5.0	240	0.7454	0.3226	0.7454	0.8634
No log	5.0417	242	0.7219	0.3571	0.7219	0.8497
No log	5.0833	244	0.7221	0.3023	0.7221	0.8498
No log	5.125	246	0.7172	0.3023	0.7172	0.8469
No log	5.1667	248	0.7197	0.2895	0.7197	0.8483
No log	5.2083	250	0.6939	0.24	0.6939	0.8330
No log	5.25	252	0.6676	0.24	0.6676	0.8170
No log	5.2917	254	0.6512	0.2609	0.6512	0.8070
No log	5.3333	256	0.6484	0.1429	0.6484	0.8053
No log	5.375	258	0.6789	0.1892	0.6789	0.8240
No log	5.4167	260	0.6744	0.1892	0.6744	0.8212
No log	5.4583	262	0.6372	0.1429	0.6372	0.7983
No log	5.5	264	0.6171	0.2609	0.6171	0.7855
No log	5.5417	266	0.6291	0.2609	0.6291	0.7932
No log	5.5833	268	0.6497	0.3514	0.6497	0.8061
No log	5.625	270	0.6837	0.3077	0.6837	0.8269
No log	5.6667	272	0.7152	0.3294	0.7152	0.8457
No log	5.7083	274	0.7352	0.3736	0.7352	0.8574
No log	5.75	276	0.7677	0.3478	0.7677	0.8762
No log	5.7917	278	0.7885	0.2921	0.7885	0.8880
No log	5.8333	280	0.7997	0.3333	0.7997	0.8943
No log	5.875	282	0.7805	0.2921	0.7805	0.8835
No log	5.9167	284	0.7544	0.3448	0.7544	0.8685
No log	5.9583	286	0.7300	0.3736	0.7300	0.8544
No log	6.0	288	0.7329	0.3736	0.7329	0.8561
No log	6.0417	290	0.7457	0.3736	0.7457	0.8636
No log	6.0833	292	0.7724	0.4138	0.7724	0.8788
No log	6.125	294	0.7742	0.3736	0.7742	0.8799
No log	6.1667	296	0.7727	0.3736	0.7727	0.8790
No log	6.2083	298	0.7747	0.3448	0.7747	0.8802
No log	6.25	300	0.7795	0.3448	0.7795	0.8829
No log	6.2917	302	0.7807	0.3448	0.7807	0.8836
No log	6.3333	304	0.7730	0.3448	0.7730	0.8792
No log	6.375	306	0.7388	0.3736	0.7388	0.8595
No log	6.4167	308	0.7255	0.3571	0.7255	0.8518
No log	6.4583	310	0.7301	0.3571	0.7301	0.8545
No log	6.5	312	0.7355	0.3736	0.7355	0.8576
No log	6.5417	314	0.7932	0.3448	0.7932	0.8906
No log	6.5833	316	0.8818	0.2340	0.8818	0.9391
No log	6.625	318	0.8779	0.2424	0.8779	0.9370
No log	6.6667	320	0.7946	0.3448	0.7946	0.8914
No log	6.7083	322	0.7190	0.3721	0.7190	0.8480
No log	6.75	324	0.7083	0.3133	0.7083	0.8416
No log	6.7917	326	0.7247	0.3133	0.7247	0.8513
No log	6.8333	328	0.7397	0.3333	0.7397	0.8600
No log	6.875	330	0.7904	0.3448	0.7904	0.8891
No log	6.9167	332	0.9055	0.1818	0.9055	0.9516
No log	6.9583	334	0.9394	0.2957	0.9394	0.9692
No log	7.0	336	0.8742	0.2174	0.8742	0.9350
No log	7.0417	338	0.7724	0.3448	0.7724	0.8789
No log	7.0833	340	0.7154	0.3721	0.7154	0.8458
No log	7.125	342	0.7112	0.3133	0.7112	0.8433
No log	7.1667	344	0.7251	0.3133	0.7251	0.8515
No log	7.2083	346	0.7446	0.3736	0.7446	0.8629
No log	7.25	348	0.7857	0.3448	0.7857	0.8864
No log	7.2917	350	0.8336	0.3864	0.8336	0.9130
No log	7.3333	352	0.8407	0.3864	0.8407	0.9169
No log	7.375	354	0.8005	0.3448	0.8005	0.8947
No log	7.4167	356	0.7604	0.3736	0.7604	0.8720
No log	7.4583	358	0.7335	0.3571	0.7335	0.8564
No log	7.5	360	0.7225	0.3571	0.7225	0.8500
No log	7.5417	362	0.7223	0.3571	0.7223	0.8499
No log	7.5833	364	0.7240	0.3544	0.7240	0.8509
No log	7.625	366	0.7391	0.3448	0.7391	0.8597
No log	7.6667	368	0.7731	0.2921	0.7731	0.8793
No log	7.7083	370	0.8407	0.2222	0.8407	0.9169
No log	7.75	372	0.8873	0.1429	0.8873	0.9420
No log	7.7917	374	0.9119	0.1758	0.9119	0.9549
No log	7.8333	376	0.8857	0.2247	0.8857	0.9411
No log	7.875	378	0.8575	0.2826	0.8575	0.9260
No log	7.9167	380	0.8146	0.2921	0.8146	0.9025
No log	7.9583	382	0.7863	0.3864	0.7863	0.8867
No log	8.0	384	0.7885	0.3864	0.7885	0.8880
No log	8.0417	386	0.8068	0.3736	0.8068	0.8982
No log	8.0833	388	0.8168	0.3736	0.8168	0.9037
No log	8.125	390	0.8307	0.3736	0.8307	0.9114
No log	8.1667	392	0.8529	0.3871	0.8529	0.9235
No log	8.2083	394	0.8686	0.3871	0.8686	0.9320
No log	8.25	396	0.8685	0.3871	0.8685	0.9319
No log	8.2917	398	0.8504	0.3871	0.8504	0.9222
No log	8.3333	400	0.8375	0.3871	0.8375	0.9152
No log	8.375	402	0.8350	0.3871	0.8350	0.9138
No log	8.4167	404	0.8340	0.3871	0.8340	0.9132
No log	8.4583	406	0.8276	0.3871	0.8276	0.9097
No log	8.5	408	0.8364	0.3400	0.8364	0.9146
No log	8.5417	410	0.8476	0.2500	0.8476	0.9207
No log	8.5833	412	0.8589	0.2500	0.8589	0.9268
No log	8.625	414	0.8564	0.2500	0.8564	0.9254
No log	8.6667	416	0.8546	0.2574	0.8546	0.9244
No log	8.7083	418	0.8542	0.3400	0.8542	0.9242
No log	8.75	420	0.8687	0.3400	0.8687	0.9321
No log	8.7917	422	0.8744	0.3400	0.8744	0.9351
No log	8.8333	424	0.8813	0.3871	0.8813	0.9388
No log	8.875	426	0.8955	0.2574	0.8955	0.9463
No log	8.9167	428	0.9066	0.2574	0.9066	0.9522
No log	8.9583	430	0.9025	0.2574	0.9025	0.9500
No log	9.0	432	0.9002	0.2574	0.9002	0.9488
No log	9.0417	434	0.8984	0.2574	0.8984	0.9479
No log	9.0833	436	0.8968	0.2574	0.8968	0.9470
No log	9.125	438	0.8897	0.2574	0.8897	0.9432
No log	9.1667	440	0.8839	0.3400	0.8839	0.9401
No log	9.2083	442	0.8775	0.3400	0.8775	0.9368
No log	9.25	444	0.8730	0.3368	0.8730	0.9344
No log	9.2917	446	0.8705	0.3368	0.8705	0.9330
No log	9.3333	448	0.8703	0.2500	0.8703	0.9329
No log	9.375	450	0.8666	0.3368	0.8666	0.9309
No log	9.4167	452	0.8617	0.3864	0.8617	0.9283
No log	9.4583	454	0.8530	0.3871	0.8530	0.9236
No log	9.5	456	0.8435	0.3871	0.8435	0.9184
No log	9.5417	458	0.8374	0.3871	0.8374	0.9151
No log	9.5833	460	0.8331	0.3871	0.8331	0.9127
No log	9.625	462	0.8291	0.3478	0.8291	0.9105
No log	9.6667	464	0.8272	0.3478	0.8272	0.9095
No log	9.7083	466	0.8244	0.3478	0.8244	0.9080
No log	9.75	468	0.8223	0.3478	0.8223	0.9068
No log	9.7917	470	0.8201	0.3478	0.8201	0.9056
No log	9.8333	472	0.8195	0.3478	0.8195	0.9052
No log	9.875	474	0.8202	0.3478	0.8202	0.9056
No log	9.9167	476	0.8210	0.3478	0.8210	0.9061
No log	9.9583	478	0.8211	0.3478	0.8211	0.9062
No log	10.0	480	0.8213	0.3478	0.8213	0.9063

Framework versions

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