Arabic_CrossPrompt_FineTuningAraBERT_noAug_TestTask8_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: 0.6637
• Qwk: 0.6356
• Mse: 0.6637
• Rmse: 0.8147

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: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	0.0196	2	4.2952	0.0102	4.2952	2.0725
No log	0.0392	4	3.2266	0.0799	3.2266	1.7963
No log	0.0588	6	1.8412	0.1386	1.8412	1.3569
No log	0.0784	8	1.0988	0.2278	1.0988	1.0482
No log	0.0980	10	1.0968	0.2094	1.0968	1.0473
No log	0.1176	12	1.1545	0.0904	1.1545	1.0745
No log	0.1373	14	1.1518	0.2008	1.1518	1.0732
No log	0.1569	16	1.2856	0.1234	1.2856	1.1338
No log	0.1765	18	1.0710	0.2542	1.0710	1.0349
No log	0.1961	20	0.9405	0.4251	0.9405	0.9698
No log	0.2157	22	0.9575	0.3779	0.9575	0.9785
No log	0.2353	24	1.0108	0.3764	1.0108	1.0054
No log	0.2549	26	1.0748	0.3427	1.0748	1.0367
No log	0.2745	28	1.0006	0.4063	1.0006	1.0003
No log	0.2941	30	0.8637	0.5009	0.8637	0.9293
No log	0.3137	32	0.8053	0.4698	0.8053	0.8974
No log	0.3333	34	0.8135	0.4257	0.8135	0.9019
No log	0.3529	36	0.8487	0.4325	0.8487	0.9213
No log	0.3725	38	0.8912	0.4374	0.8912	0.9440
No log	0.3922	40	0.8144	0.4875	0.8144	0.9024
No log	0.4118	42	0.7211	0.5815	0.7211	0.8492
No log	0.4314	44	0.7169	0.5865	0.7169	0.8467
No log	0.4510	46	0.7229	0.5194	0.7229	0.8502
No log	0.4706	48	0.7373	0.5317	0.7373	0.8586
No log	0.4902	50	0.7474	0.5413	0.7474	0.8645
No log	0.5098	52	0.7460	0.5308	0.7460	0.8637
No log	0.5294	54	0.7572	0.5087	0.7572	0.8702
No log	0.5490	56	0.7854	0.4931	0.7854	0.8863
No log	0.5686	58	0.8381	0.4277	0.8381	0.9155
No log	0.5882	60	0.9500	0.3694	0.9500	0.9747
No log	0.6078	62	0.9132	0.4035	0.9132	0.9556
No log	0.6275	64	0.8686	0.4811	0.8686	0.9320
No log	0.6471	66	0.7388	0.5726	0.7388	0.8595
No log	0.6667	68	0.7300	0.5573	0.7300	0.8544
No log	0.6863	70	0.7859	0.5380	0.7859	0.8865
No log	0.7059	72	0.8167	0.5099	0.8167	0.9037
No log	0.7255	74	0.9063	0.5092	0.9063	0.9520
No log	0.7451	76	0.8688	0.4810	0.8688	0.9321
No log	0.7647	78	0.8280	0.5209	0.8280	0.9100
No log	0.7843	80	0.7573	0.5683	0.7573	0.8702
No log	0.8039	82	0.7654	0.5697	0.7654	0.8749
No log	0.8235	84	0.7306	0.5834	0.7306	0.8547
No log	0.8431	86	0.7655	0.5556	0.7655	0.8749
No log	0.8627	88	1.0433	0.4724	1.0433	1.0214
No log	0.8824	90	1.1994	0.4390	1.1994	1.0952
No log	0.9020	92	0.9817	0.5090	0.9817	0.9908
No log	0.9216	94	0.6939	0.5289	0.6939	0.8330
No log	0.9412	96	0.6782	0.5800	0.6782	0.8235
No log	0.9608	98	0.6669	0.5468	0.6669	0.8166
No log	0.9804	100	0.6804	0.5536	0.6804	0.8249
No log	1.0	102	0.6890	0.5708	0.6890	0.8301
No log	1.0196	104	0.7477	0.5812	0.7477	0.8647
No log	1.0392	106	0.7234	0.6064	0.7234	0.8505
No log	1.0588	108	0.6907	0.5935	0.6907	0.8311
No log	1.0784	110	0.7004	0.6393	0.7004	0.8369
No log	1.0980	112	0.6759	0.6637	0.6759	0.8221
No log	1.1176	114	0.6917	0.6437	0.6917	0.8317
No log	1.1373	116	0.6841	0.6441	0.6841	0.8271
No log	1.1569	118	0.7122	0.5814	0.7122	0.8439
No log	1.1765	120	0.8183	0.4949	0.8183	0.9046
No log	1.1961	122	0.8523	0.4799	0.8523	0.9232
No log	1.2157	124	0.8479	0.5240	0.8479	0.9208
No log	1.2353	126	0.8277	0.5782	0.8277	0.9098
No log	1.2549	128	0.8707	0.6108	0.8707	0.9331
No log	1.2745	130	0.7377	0.6903	0.7377	0.8589
No log	1.2941	132	0.6445	0.6575	0.6445	0.8028
No log	1.3137	134	0.6641	0.6654	0.6641	0.8149
No log	1.3333	136	0.7284	0.6182	0.7284	0.8534
No log	1.3529	138	0.7679	0.6292	0.7679	0.8763
No log	1.3725	140	0.6204	0.6527	0.6204	0.7877
No log	1.3922	142	0.6521	0.6035	0.6521	0.8075
No log	1.4118	144	0.6780	0.5941	0.6780	0.8234
No log	1.4314	146	0.6080	0.6319	0.6080	0.7797
No log	1.4510	148	0.6093	0.6444	0.6093	0.7806
No log	1.4706	150	0.7406	0.6425	0.7406	0.8606
No log	1.4902	152	0.7195	0.6664	0.7195	0.8482
No log	1.5098	154	0.7023	0.6695	0.7023	0.8381
No log	1.5294	156	0.6536	0.6639	0.6536	0.8085
No log	1.5490	158	0.7030	0.6854	0.7030	0.8384
No log	1.5686	160	0.7469	0.6724	0.7469	0.8642
No log	1.5882	162	0.6844	0.6661	0.6844	0.8273
No log	1.6078	164	0.6306	0.6142	0.6306	0.7941
No log	1.6275	166	0.6222	0.6111	0.6222	0.7888
No log	1.6471	168	0.7040	0.6631	0.7040	0.8391
No log	1.6667	170	0.8624	0.6188	0.8624	0.9286
No log	1.6863	172	0.9003	0.5841	0.9003	0.9489
No log	1.7059	174	0.7114	0.6047	0.7114	0.8434
No log	1.7255	176	0.6270	0.6387	0.6270	0.7918
No log	1.7451	178	0.7834	0.6244	0.7834	0.8851
No log	1.7647	180	0.7746	0.6135	0.7746	0.8801
No log	1.7843	182	0.6805	0.5776	0.6805	0.8249
No log	1.8039	184	0.6996	0.4999	0.6996	0.8364
No log	1.8235	186	0.8609	0.5141	0.8609	0.9279
No log	1.8431	188	0.9514	0.4900	0.9514	0.9754
No log	1.8627	190	0.9757	0.5319	0.9757	0.9878
No log	1.8824	192	0.8713	0.5884	0.8713	0.9335
No log	1.9020	194	0.6578	0.6685	0.6578	0.8110
No log	1.9216	196	0.6701	0.6870	0.6701	0.8186
No log	1.9412	198	0.8171	0.6909	0.8171	0.9040
No log	1.9608	200	0.9065	0.6280	0.9065	0.9521
No log	1.9804	202	0.7902	0.6462	0.7902	0.8889
No log	2.0	204	0.6671	0.6583	0.6671	0.8167
No log	2.0196	206	0.6646	0.6442	0.6646	0.8152
No log	2.0392	208	0.7101	0.6132	0.7101	0.8426
No log	2.0588	210	0.7350	0.6091	0.7350	0.8573
No log	2.0784	212	0.7174	0.6268	0.7174	0.8470
No log	2.0980	214	0.7046	0.6320	0.7046	0.8394
No log	2.1176	216	0.6900	0.6289	0.6900	0.8307
No log	2.1373	218	0.6344	0.6392	0.6344	0.7965
No log	2.1569	220	0.6480	0.6577	0.6480	0.8050
No log	2.1765	222	0.7225	0.6413	0.7225	0.8500
No log	2.1961	224	0.6654	0.6659	0.6654	0.8157
No log	2.2157	226	0.5786	0.6383	0.5786	0.7606
No log	2.2353	228	0.5798	0.6740	0.5798	0.7615
No log	2.2549	230	0.5872	0.6672	0.5872	0.7663
No log	2.2745	232	0.6322	0.6909	0.6322	0.7951
No log	2.2941	234	0.7586	0.6493	0.7586	0.8710
No log	2.3137	236	0.7852	0.6383	0.7852	0.8861
No log	2.3333	238	0.7052	0.6798	0.7052	0.8398
No log	2.3529	240	0.6188	0.6954	0.6188	0.7866
No log	2.3725	242	0.6620	0.6889	0.6620	0.8136
No log	2.3922	244	0.6580	0.6528	0.6580	0.8112
No log	2.4118	246	0.6573	0.6404	0.6573	0.8107
No log	2.4314	248	0.8856	0.5867	0.8856	0.9411
No log	2.4510	250	1.1315	0.5154	1.1315	1.0637
No log	2.4706	252	1.0135	0.5270	1.0135	1.0067
No log	2.4902	254	0.7767	0.5464	0.7767	0.8813
No log	2.5098	256	0.6975	0.5738	0.6975	0.8352
No log	2.5294	258	0.7170	0.5700	0.7170	0.8468
No log	2.5490	260	0.8040	0.5864	0.8040	0.8966
No log	2.5686	262	0.7430	0.6235	0.7430	0.8620
No log	2.5882	264	0.6681	0.6426	0.6681	0.8174
No log	2.6078	266	0.6818	0.6616	0.6818	0.8257
No log	2.6275	268	0.7374	0.6819	0.7374	0.8587
No log	2.6471	270	0.6832	0.6952	0.6832	0.8266
No log	2.6667	272	0.6918	0.6998	0.6918	0.8318
No log	2.6863	274	0.9110	0.6552	0.9110	0.9544
No log	2.7059	276	1.1775	0.6085	1.1775	1.0851
No log	2.7255	278	1.0729	0.6115	1.0729	1.0358
No log	2.7451	280	0.8355	0.6284	0.8355	0.9140
No log	2.7647	282	0.6621	0.6563	0.6621	0.8137
No log	2.7843	284	0.6377	0.6714	0.6377	0.7985
No log	2.8039	286	0.6439	0.6876	0.6439	0.8024
No log	2.8235	288	0.6961	0.6412	0.6961	0.8343
No log	2.8431	290	0.9360	0.5822	0.9360	0.9675
No log	2.8627	292	1.0942	0.5635	1.0942	1.0461
No log	2.8824	294	0.9331	0.5735	0.9331	0.9660
No log	2.9020	296	0.7332	0.6367	0.7332	0.8562
No log	2.9216	298	0.6417	0.6417	0.6417	0.8010
No log	2.9412	300	0.6453	0.6413	0.6453	0.8033
No log	2.9608	302	0.7120	0.6062	0.7120	0.8438
No log	2.9804	304	0.6610	0.6344	0.6610	0.8130
No log	3.0	306	0.6399	0.6456	0.6399	0.7999
No log	3.0196	308	0.8032	0.6526	0.8032	0.8962
No log	3.0392	310	0.8972	0.6433	0.8972	0.9472
No log	3.0588	312	0.9137	0.6394	0.9137	0.9559
No log	3.0784	314	0.7396	0.6746	0.7396	0.8600
No log	3.0980	316	0.6958	0.6370	0.6958	0.8341
No log	3.1176	318	0.7007	0.6299	0.7007	0.8371
No log	3.1373	320	0.6408	0.5930	0.6408	0.8005
No log	3.1569	322	0.6358	0.5737	0.6358	0.7974
No log	3.1765	324	0.6347	0.5766	0.6347	0.7967
No log	3.1961	326	0.6488	0.6196	0.6488	0.8055
No log	3.2157	328	0.7554	0.6606	0.7554	0.8691
No log	3.2353	330	0.7893	0.6370	0.7893	0.8884
No log	3.2549	332	0.8156	0.6470	0.8156	0.9031
No log	3.2745	334	0.6970	0.6564	0.6970	0.8349
No log	3.2941	336	0.6706	0.6599	0.6706	0.8189
No log	3.3137	338	0.6852	0.6362	0.6852	0.8278
No log	3.3333	340	0.6440	0.6605	0.6440	0.8025
No log	3.3529	342	0.7842	0.6466	0.7842	0.8855
No log	3.3725	344	1.2209	0.5235	1.2209	1.1050
No log	3.3922	346	1.3001	0.4906	1.3001	1.1402
No log	3.4118	348	0.9946	0.5760	0.9946	0.9973
No log	3.4314	350	0.6702	0.6678	0.6702	0.8186
No log	3.4510	352	0.6631	0.6439	0.6631	0.8143
No log	3.4706	354	0.6758	0.6311	0.6758	0.8220
No log	3.4902	356	0.6604	0.6891	0.6604	0.8126
No log	3.5098	358	0.9361	0.6100	0.9361	0.9675
No log	3.5294	360	1.2398	0.5575	1.2398	1.1135
No log	3.5490	362	1.1421	0.5672	1.1421	1.0687
No log	3.5686	364	0.8577	0.6494	0.8577	0.9261
No log	3.5882	366	0.7330	0.6684	0.7330	0.8561
No log	3.6078	368	0.7924	0.6438	0.7924	0.8902
No log	3.6275	370	0.7405	0.6515	0.7405	0.8605
No log	3.6471	372	0.6868	0.6605	0.6868	0.8288
No log	3.6667	374	0.7430	0.6562	0.7430	0.8619
No log	3.6863	376	0.9368	0.5893	0.9368	0.9679
No log	3.7059	378	1.0358	0.5665	1.0358	1.0177
No log	3.7255	380	1.0289	0.5772	1.0289	1.0144
No log	3.7451	382	0.8941	0.6492	0.8941	0.9456
No log	3.7647	384	0.7306	0.6657	0.7306	0.8547
No log	3.7843	386	0.7037	0.6764	0.7037	0.8389
No log	3.8039	388	0.7334	0.6577	0.7334	0.8564
No log	3.8235	390	0.7398	0.6592	0.7398	0.8601
No log	3.8431	392	0.7918	0.6615	0.7918	0.8898
No log	3.8627	394	0.8550	0.6641	0.8550	0.9247
No log	3.8824	396	0.9668	0.6570	0.9668	0.9832
No log	3.9020	398	0.7953	0.6655	0.7953	0.8918
No log	3.9216	400	0.6472	0.6941	0.6472	0.8045
No log	3.9412	402	0.6327	0.6735	0.6327	0.7954
No log	3.9608	404	0.6214	0.6756	0.6214	0.7883
No log	3.9804	406	0.7604	0.6664	0.7604	0.8720
No log	4.0	408	0.9570	0.5896	0.9570	0.9783
No log	4.0196	410	0.8949	0.6154	0.8949	0.9460
No log	4.0392	412	0.8523	0.6359	0.8523	0.9232
No log	4.0588	414	0.6731	0.6932	0.6731	0.8204
No log	4.0784	416	0.6122	0.7033	0.6122	0.7824
No log	4.0980	418	0.6572	0.6972	0.6572	0.8107
No log	4.1176	420	0.7898	0.6984	0.7898	0.8887
No log	4.1373	422	1.2016	0.6200	1.2016	1.0962
No log	4.1569	424	1.2801	0.6165	1.2801	1.1314
No log	4.1765	426	1.0264	0.6515	1.0264	1.0131
No log	4.1961	428	0.7693	0.6649	0.7693	0.8771
No log	4.2157	430	0.6625	0.6731	0.6625	0.8139
No log	4.2353	432	0.6647	0.6333	0.6647	0.8153
No log	4.2549	434	0.7027	0.6205	0.7027	0.8383
No log	4.2745	436	0.8217	0.5862	0.8217	0.9065
No log	4.2941	438	0.8034	0.6025	0.8034	0.8963
No log	4.3137	440	0.7041	0.6427	0.7041	0.8391
No log	4.3333	442	0.6447	0.6633	0.6447	0.8029
No log	4.3529	444	0.6396	0.6758	0.6396	0.7997
No log	4.3725	446	0.6819	0.6481	0.6819	0.8258
No log	4.3922	448	0.7204	0.6694	0.7204	0.8488
No log	4.4118	450	0.7344	0.6998	0.7344	0.8570
No log	4.4314	452	0.7389	0.7045	0.7389	0.8596
No log	4.4510	454	0.7830	0.6996	0.7830	0.8849
No log	4.4706	456	0.7596	0.7124	0.7596	0.8715
No log	4.4902	458	0.7509	0.7168	0.7509	0.8665
No log	4.5098	460	0.7286	0.6891	0.7286	0.8536
No log	4.5294	462	0.7226	0.6656	0.7226	0.8501
No log	4.5490	464	0.8479	0.6008	0.8479	0.9208
No log	4.5686	466	0.9028	0.5806	0.9028	0.9501
No log	4.5882	468	0.7854	0.6231	0.7854	0.8862
No log	4.6078	470	0.6817	0.6583	0.6817	0.8256
No log	4.6275	472	0.6759	0.6559	0.6759	0.8222
No log	4.6471	474	0.6931	0.6797	0.6931	0.8325
No log	4.6667	476	0.8320	0.6271	0.8320	0.9121
No log	4.6863	478	0.9053	0.6113	0.9053	0.9515
No log	4.7059	480	0.9333	0.6096	0.9333	0.9661
No log	4.7255	482	0.8155	0.6333	0.8155	0.9031
No log	4.7451	484	0.7290	0.6645	0.7290	0.8538
No log	4.7647	486	0.6305	0.6741	0.6305	0.7941
No log	4.7843	488	0.5985	0.6800	0.5985	0.7736
No log	4.8039	490	0.6149	0.6623	0.6149	0.7841
No log	4.8235	492	0.6850	0.6384	0.6850	0.8277
No log	4.8431	494	0.7936	0.6211	0.7936	0.8908
No log	4.8627	496	0.8023	0.6104	0.8023	0.8957
No log	4.8824	498	0.7001	0.6004	0.7001	0.8367
0.5778	4.9020	500	0.6068	0.6467	0.6068	0.7790
0.5778	4.9216	502	0.6518	0.6368	0.6518	0.8073
0.5778	4.9412	504	0.6472	0.6654	0.6472	0.8045
0.5778	4.9608	506	0.6070	0.6702	0.6070	0.7791
0.5778	4.9804	508	0.7523	0.6564	0.7523	0.8674
0.5778	5.0	510	0.8719	0.6426	0.8719	0.9337
0.5778	5.0196	512	0.8401	0.6582	0.8401	0.9166
0.5778	5.0392	514	0.6989	0.7079	0.6989	0.8360
0.5778	5.0588	516	0.6384	0.6734	0.6384	0.7990
0.5778	5.0784	518	0.6617	0.6538	0.6617	0.8134
0.5778	5.0980	520	0.6237	0.6772	0.6237	0.7897
0.5778	5.1176	522	0.6969	0.6928	0.6969	0.8348
0.5778	5.1373	524	0.8394	0.6478	0.8394	0.9162
0.5778	5.1569	526	0.8070	0.6241	0.8070	0.8983
0.5778	5.1765	528	0.7122	0.6371	0.7122	0.8439
0.5778	5.1961	530	0.6388	0.6672	0.6388	0.7992
0.5778	5.2157	532	0.6036	0.6680	0.6036	0.7769
0.5778	5.2353	534	0.6094	0.6504	0.6094	0.7807
0.5778	5.2549	536	0.6240	0.6934	0.6240	0.7900
0.5778	5.2745	538	0.7745	0.6495	0.7745	0.8800
0.5778	5.2941	540	0.9460	0.5997	0.9460	0.9726
0.5778	5.3137	542	1.0257	0.5844	1.0257	1.0128
0.5778	5.3333	544	0.8669	0.6026	0.8669	0.9311
0.5778	5.3529	546	0.6861	0.6424	0.6861	0.8283
0.5778	5.3725	548	0.6637	0.6356	0.6637	0.8147

Framework versions

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