ArabicNewSplits6_FineTuningAraBERTFreeze_run2_AugV5_k6_task1_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: 1.0096
• Qwk: 0.6079
• Mse: 1.0096
• Rmse: 1.0048

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	0.1176	2	7.9024	-0.0447	7.9024	2.8111
No log	0.2353	4	5.6454	-0.0450	5.6454	2.3760
No log	0.3529	6	3.9886	0.0219	3.9886	1.9972
No log	0.4706	8	2.9356	0.0888	2.9356	1.7134
No log	0.5882	10	2.1736	0.1248	2.1736	1.4743
No log	0.7059	12	1.6412	0.1628	1.6412	1.2811
No log	0.8235	14	1.3182	0.2991	1.3182	1.1481
No log	0.9412	16	1.1301	0.4513	1.1301	1.0631
No log	1.0588	18	1.0299	0.4545	1.0299	1.0148
No log	1.1765	20	1.0134	0.4930	1.0134	1.0067
No log	1.2941	22	0.9969	0.4897	0.9969	0.9984
No log	1.4118	24	0.9250	0.4890	0.9250	0.9618
No log	1.5294	26	0.8670	0.4676	0.8670	0.9311
No log	1.6471	28	0.8441	0.4942	0.8441	0.9187
No log	1.7647	30	0.8446	0.5092	0.8446	0.9190
No log	1.8824	32	0.9663	0.4831	0.9663	0.9830
No log	2.0	34	1.2875	0.4196	1.2875	1.1347
No log	2.1176	36	1.5026	0.3968	1.5026	1.2258
No log	2.2353	38	1.4119	0.3856	1.4119	1.1883
No log	2.3529	40	1.1049	0.5004	1.1049	1.0512
No log	2.4706	42	0.8569	0.5537	0.8569	0.9257
No log	2.5882	44	0.8040	0.5961	0.8040	0.8967
No log	2.7059	46	0.7705	0.6191	0.7705	0.8778
No log	2.8235	48	0.8564	0.5562	0.8564	0.9254
No log	2.9412	50	1.0212	0.5085	1.0212	1.0105
No log	3.0588	52	1.2001	0.4642	1.2001	1.0955
No log	3.1765	54	1.1439	0.4779	1.1439	1.0695
No log	3.2941	56	0.9754	0.5398	0.9754	0.9876
No log	3.4118	58	0.8243	0.6057	0.8243	0.9079
No log	3.5294	60	0.7516	0.6441	0.7516	0.8669
No log	3.6471	62	0.7753	0.6360	0.7753	0.8805
No log	3.7647	64	0.8231	0.6321	0.8231	0.9072
No log	3.8824	66	0.7811	0.6401	0.7811	0.8838
No log	4.0	68	0.6940	0.6840	0.6940	0.8331
No log	4.1176	70	0.6354	0.7023	0.6354	0.7971
No log	4.2353	72	0.6447	0.7082	0.6447	0.8029
No log	4.3529	74	0.6646	0.7068	0.6646	0.8152
No log	4.4706	76	0.6863	0.7068	0.6863	0.8284
No log	4.5882	78	0.6601	0.6928	0.6601	0.8124
No log	4.7059	80	0.6514	0.6928	0.6514	0.8071
No log	4.8235	82	0.6338	0.7174	0.6338	0.7961
No log	4.9412	84	0.6400	0.7252	0.6400	0.8000
No log	5.0588	86	0.7165	0.6734	0.7165	0.8465
No log	5.1765	88	1.0095	0.5778	1.0095	1.0048
No log	5.2941	90	1.1837	0.5256	1.1837	1.0880
No log	5.4118	92	1.0678	0.5480	1.0678	1.0334
No log	5.5294	94	0.8206	0.6522	0.8206	0.9059
No log	5.6471	96	0.6552	0.7163	0.6552	0.8094
No log	5.7647	98	0.6214	0.7261	0.6214	0.7883
No log	5.8824	100	0.6237	0.7295	0.6237	0.7898
No log	6.0	102	0.6280	0.7312	0.6280	0.7925
No log	6.1176	104	0.6314	0.7352	0.6314	0.7946
No log	6.2353	106	0.6846	0.7064	0.6846	0.8274
No log	6.3529	108	0.8579	0.6260	0.8579	0.9262
No log	6.4706	110	0.9537	0.6408	0.9537	0.9766
No log	6.5882	112	0.9229	0.6365	0.9229	0.9607
No log	6.7059	114	0.8900	0.6191	0.8900	0.9434
No log	6.8235	116	0.7690	0.6516	0.7690	0.8769
No log	6.9412	118	0.6356	0.7116	0.6356	0.7973
No log	7.0588	120	0.6352	0.7303	0.6352	0.7970
No log	7.1765	122	0.7238	0.6859	0.7238	0.8508
No log	7.2941	124	0.6832	0.7110	0.6832	0.8265
No log	7.4118	126	0.5925	0.7321	0.5925	0.7698
No log	7.5294	128	0.6473	0.7142	0.6473	0.8045
No log	7.6471	130	0.8007	0.6630	0.8007	0.8948
No log	7.7647	132	0.8649	0.6050	0.8649	0.9300
No log	7.8824	134	0.7777	0.6739	0.7777	0.8819
No log	8.0	136	0.7081	0.6917	0.7081	0.8415
No log	8.1176	138	0.6353	0.6886	0.6353	0.7971
No log	8.2353	140	0.6131	0.6871	0.6131	0.7830
No log	8.3529	142	0.5983	0.7093	0.5983	0.7735
No log	8.4706	144	0.5991	0.7181	0.5991	0.7740
No log	8.5882	146	0.6477	0.6988	0.6477	0.8048
No log	8.7059	148	0.6875	0.7023	0.6875	0.8291
No log	8.8235	150	0.6649	0.6956	0.6649	0.8154
No log	8.9412	152	0.6297	0.7016	0.6297	0.7935
No log	9.0588	154	0.6562	0.7088	0.6562	0.8100
No log	9.1765	156	0.6519	0.7052	0.6519	0.8074
No log	9.2941	158	0.6840	0.7018	0.6840	0.8271
No log	9.4118	160	0.6719	0.6828	0.6719	0.8197
No log	9.5294	162	0.6304	0.7185	0.6304	0.7940
No log	9.6471	164	0.6463	0.7364	0.6463	0.8039
No log	9.7647	166	0.6527	0.7325	0.6527	0.8079
No log	9.8824	168	0.6487	0.7387	0.6487	0.8054
No log	10.0	170	0.6481	0.7232	0.6481	0.8051
No log	10.1176	172	0.6649	0.6660	0.6649	0.8154
No log	10.2353	174	0.7007	0.6890	0.7007	0.8371
No log	10.3529	176	0.7710	0.6533	0.7710	0.8781
No log	10.4706	178	0.7651	0.6647	0.7651	0.8747
No log	10.5882	180	0.6873	0.6795	0.6873	0.8290
No log	10.7059	182	0.6861	0.6851	0.6861	0.8283
No log	10.8235	184	0.7159	0.6958	0.7159	0.8461
No log	10.9412	186	0.7257	0.6989	0.7257	0.8519
No log	11.0588	188	0.7629	0.6590	0.7629	0.8734
No log	11.1765	190	0.8306	0.6250	0.8306	0.9114
No log	11.2941	192	0.7678	0.6560	0.7678	0.8762
No log	11.4118	194	0.6934	0.6902	0.6934	0.8327
No log	11.5294	196	0.6665	0.7223	0.6665	0.8164
No log	11.6471	198	0.6686	0.7299	0.6686	0.8177
No log	11.7647	200	0.6670	0.7238	0.6670	0.8167
No log	11.8824	202	0.6929	0.7319	0.6929	0.8324
No log	12.0	204	0.7316	0.7114	0.7316	0.8553
No log	12.1176	206	0.7611	0.6840	0.7611	0.8724
No log	12.2353	208	0.7027	0.7172	0.7027	0.8383
No log	12.3529	210	0.6876	0.7131	0.6876	0.8292
No log	12.4706	212	0.6952	0.6963	0.6952	0.8338
No log	12.5882	214	0.7126	0.6545	0.7126	0.8442
No log	12.7059	216	0.7002	0.6701	0.7002	0.8368
No log	12.8235	218	0.7212	0.7043	0.7212	0.8492
No log	12.9412	220	0.7339	0.7038	0.7339	0.8567
No log	13.0588	222	0.6882	0.7209	0.6882	0.8296
No log	13.1765	224	0.6873	0.6670	0.6873	0.8290
No log	13.2941	226	0.7298	0.6663	0.7298	0.8543
No log	13.4118	228	0.7120	0.6528	0.7120	0.8438
No log	13.5294	230	0.7003	0.7196	0.7003	0.8369
No log	13.6471	232	0.7202	0.7084	0.7202	0.8486
No log	13.7647	234	0.7363	0.7064	0.7363	0.8581
No log	13.8824	236	0.7170	0.7144	0.7170	0.8468
No log	14.0	238	0.7106	0.7230	0.7106	0.8430
No log	14.1176	240	0.7025	0.6993	0.7025	0.8382
No log	14.2353	242	0.7149	0.6844	0.7149	0.8455
No log	14.3529	244	0.7065	0.7068	0.7065	0.8405
No log	14.4706	246	0.7490	0.7251	0.7490	0.8654
No log	14.5882	248	0.7782	0.7218	0.7782	0.8822
No log	14.7059	250	0.8505	0.6565	0.8505	0.9222
No log	14.8235	252	0.8210	0.6650	0.8210	0.9061
No log	14.9412	254	0.7577	0.6850	0.7577	0.8705
No log	15.0588	256	0.7743	0.6972	0.7743	0.8799
No log	15.1765	258	0.7957	0.6935	0.7957	0.8920
No log	15.2941	260	0.8347	0.7074	0.8347	0.9136
No log	15.4118	262	0.8742	0.6671	0.8742	0.9350
No log	15.5294	264	0.8481	0.6768	0.8481	0.9209
No log	15.6471	266	0.7958	0.6983	0.7958	0.8921
No log	15.7647	268	0.7933	0.6750	0.7933	0.8907
No log	15.8824	270	0.7801	0.6750	0.7801	0.8832
No log	16.0	272	0.7752	0.7101	0.7752	0.8804
No log	16.1176	274	0.7689	0.6941	0.7689	0.8769
No log	16.2353	276	0.7761	0.6756	0.7761	0.8810
No log	16.3529	278	0.7736	0.6668	0.7736	0.8795
No log	16.4706	280	0.7665	0.7065	0.7665	0.8755
No log	16.5882	282	0.7841	0.6959	0.7841	0.8855
No log	16.7059	284	0.7778	0.6894	0.7778	0.8820
No log	16.8235	286	0.7940	0.6475	0.7940	0.8910
No log	16.9412	288	0.7739	0.6876	0.7739	0.8797
No log	17.0588	290	0.7555	0.6876	0.7555	0.8692
No log	17.1765	292	0.7289	0.6936	0.7289	0.8537
No log	17.2941	294	0.7299	0.6842	0.7299	0.8544
No log	17.4118	296	0.7736	0.7090	0.7736	0.8795
No log	17.5294	298	0.7573	0.7090	0.7573	0.8702
No log	17.6471	300	0.7102	0.7050	0.7102	0.8427
No log	17.7647	302	0.6938	0.6663	0.6938	0.8329
No log	17.8824	304	0.6896	0.6529	0.6896	0.8304
No log	18.0	306	0.7009	0.6608	0.7009	0.8372
No log	18.1176	308	0.6938	0.6819	0.6938	0.8329
No log	18.2353	310	0.7162	0.6989	0.7162	0.8463
No log	18.3529	312	0.7313	0.6969	0.7313	0.8552
No log	18.4706	314	0.7127	0.6768	0.7127	0.8442
No log	18.5882	316	0.7495	0.6567	0.7495	0.8657
No log	18.7059	318	0.8344	0.6252	0.8344	0.9134
No log	18.8235	320	0.7898	0.6183	0.7898	0.8887
No log	18.9412	322	0.7321	0.6845	0.7321	0.8556
No log	19.0588	324	0.7753	0.7196	0.7753	0.8805
No log	19.1765	326	0.8550	0.6628	0.8550	0.9247
No log	19.2941	328	0.9150	0.6275	0.9150	0.9565
No log	19.4118	330	0.8323	0.6903	0.8323	0.9123
No log	19.5294	332	0.7261	0.7099	0.7261	0.8521
No log	19.6471	334	0.7102	0.6739	0.7102	0.8427
No log	19.7647	336	0.7166	0.6622	0.7166	0.8466
No log	19.8824	338	0.7319	0.6921	0.7319	0.8555
No log	20.0	340	0.7770	0.7	0.7770	0.8815
No log	20.1176	342	0.8175	0.7016	0.8175	0.9042
No log	20.2353	344	0.8234	0.7003	0.8234	0.9074
No log	20.3529	346	0.7810	0.6651	0.7810	0.8837
No log	20.4706	348	0.7823	0.6502	0.7823	0.8845
No log	20.5882	350	0.7931	0.6719	0.7931	0.8905
No log	20.7059	352	0.8038	0.6749	0.8038	0.8965
No log	20.8235	354	0.8715	0.6995	0.8715	0.9335
No log	20.9412	356	0.9899	0.5984	0.9899	0.9949
No log	21.0588	358	0.9989	0.5984	0.9989	0.9994
No log	21.1765	360	0.9564	0.6196	0.9564	0.9780
No log	21.2941	362	0.8686	0.6776	0.8686	0.9320
No log	21.4118	364	0.8137	0.6512	0.8137	0.9020
No log	21.5294	366	0.8001	0.6519	0.8001	0.8945
No log	21.6471	368	0.7917	0.6693	0.7917	0.8898
No log	21.7647	370	0.8397	0.6924	0.8397	0.9163
No log	21.8824	372	0.8851	0.6474	0.8851	0.9408
No log	22.0	374	0.8751	0.6474	0.8751	0.9355
No log	22.1176	376	0.8136	0.6818	0.8136	0.9020
No log	22.2353	378	0.7557	0.6656	0.7557	0.8693
No log	22.3529	380	0.7534	0.6566	0.7534	0.8680
No log	22.4706	382	0.7391	0.6605	0.7391	0.8597
No log	22.5882	384	0.7591	0.6868	0.7591	0.8713
No log	22.7059	386	0.7747	0.6880	0.7747	0.8802
No log	22.8235	388	0.7408	0.6910	0.7408	0.8607
No log	22.9412	390	0.7431	0.6574	0.7431	0.8620
No log	23.0588	392	0.8522	0.6404	0.8522	0.9231
No log	23.1765	394	0.9163	0.6486	0.9163	0.9572
No log	23.2941	396	0.8167	0.6637	0.8167	0.9037
No log	23.4118	398	0.7240	0.6644	0.7240	0.8509
No log	23.5294	400	0.7598	0.7159	0.7598	0.8717
No log	23.6471	402	0.7603	0.7173	0.7603	0.8720
No log	23.7647	404	0.8004	0.6998	0.8004	0.8947
No log	23.8824	406	0.8089	0.6758	0.8089	0.8994
No log	24.0	408	0.7550	0.7126	0.7550	0.8689
No log	24.1176	410	0.7189	0.6877	0.7189	0.8479
No log	24.2353	412	0.7222	0.6874	0.7222	0.8498
No log	24.3529	414	0.7345	0.6788	0.7345	0.8570
No log	24.4706	416	0.7433	0.6850	0.7433	0.8622
No log	24.5882	418	0.7992	0.7039	0.7992	0.8940
No log	24.7059	420	0.9320	0.6324	0.9320	0.9654
No log	24.8235	422	0.9466	0.6324	0.9466	0.9730
No log	24.9412	424	0.8404	0.6897	0.8404	0.9167
No log	25.0588	426	0.7777	0.6992	0.7777	0.8819
No log	25.1765	428	0.7361	0.6743	0.7361	0.8579
No log	25.2941	430	0.7513	0.6982	0.7513	0.8668
No log	25.4118	432	0.8045	0.6898	0.8045	0.8970
No log	25.5294	434	0.8456	0.6441	0.8456	0.9196
No log	25.6471	436	0.8488	0.6536	0.8488	0.9213
No log	25.7647	438	0.9006	0.6361	0.9006	0.9490
No log	25.8824	440	0.9736	0.6396	0.9736	0.9867
No log	26.0	442	0.9820	0.6396	0.9820	0.9910
No log	26.1176	444	0.9275	0.6361	0.9275	0.9631
No log	26.2353	446	0.8110	0.6838	0.8110	0.9006
No log	26.3529	448	0.7609	0.6703	0.7609	0.8723
No log	26.4706	450	0.7643	0.6690	0.7643	0.8742
No log	26.5882	452	0.7829	0.6845	0.7829	0.8848
No log	26.7059	454	0.9109	0.6383	0.9109	0.9544
No log	26.8235	456	1.0040	0.6204	1.0040	1.0020
No log	26.9412	458	0.9586	0.6396	0.9586	0.9791
No log	27.0588	460	0.8891	0.6434	0.8891	0.9429
No log	27.1765	462	0.9398	0.6296	0.9398	0.9694
No log	27.2941	464	0.9552	0.6174	0.9552	0.9773
No log	27.4118	466	0.9222	0.6390	0.9222	0.9603
No log	27.5294	468	0.8694	0.6350	0.8694	0.9324
No log	27.6471	470	0.8292	0.7058	0.8292	0.9106
No log	27.7647	472	0.8311	0.7058	0.8311	0.9117
No log	27.8824	474	0.8293	0.7137	0.8293	0.9107
No log	28.0	476	0.8380	0.6697	0.8380	0.9154
No log	28.1176	478	0.9079	0.6333	0.9079	0.9529
No log	28.2353	480	0.9155	0.6276	0.9155	0.9568
No log	28.3529	482	0.8537	0.6562	0.8537	0.9240
No log	28.4706	484	0.7946	0.6833	0.7946	0.8914
No log	28.5882	486	0.7814	0.6546	0.7814	0.8840
No log	28.7059	488	0.7863	0.6703	0.7863	0.8867
No log	28.8235	490	0.8083	0.6889	0.8083	0.8991
No log	28.9412	492	0.8076	0.6797	0.8076	0.8987
No log	29.0588	494	0.7958	0.6756	0.7958	0.8921
No log	29.1765	496	0.7926	0.6726	0.7926	0.8903
No log	29.2941	498	0.8039	0.6768	0.8039	0.8966
0.5502	29.4118	500	0.8259	0.6738	0.8259	0.9088
0.5502	29.5294	502	0.8232	0.6686	0.8232	0.9073
0.5502	29.6471	504	0.8144	0.6819	0.8144	0.9024
0.5502	29.7647	506	0.8565	0.6683	0.8565	0.9255
0.5502	29.8824	508	0.8664	0.6683	0.8664	0.9308
0.5502	30.0	510	0.8638	0.6683	0.8638	0.9294
0.5502	30.1176	512	0.8297	0.6756	0.8297	0.9109
0.5502	30.2353	514	0.8409	0.6649	0.8409	0.9170
0.5502	30.3529	516	0.9036	0.6371	0.9036	0.9506
0.5502	30.4706	518	0.9768	0.6043	0.9768	0.9883
0.5502	30.5882	520	1.0323	0.5808	1.0323	1.0160
0.5502	30.7059	522	1.0096	0.6079	1.0096	1.0048

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.2.0
• Tokenizers 0.19.1