Arabic_CrossPrompt_FineTuningAraBERT_noAug_TestTask3_vocabulary

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: 0.5136
• Qwk: 0.6644
• Mse: 0.5136
• Rmse: 0.7166

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	0.0194	2	4.9158	-0.0091	4.9158	2.2172
No log	0.0388	4	3.2213	0.0932	3.2213	1.7948
No log	0.0583	6	2.0330	0.0181	2.0330	1.4258
No log	0.0777	8	1.1038	0.1866	1.1038	1.0506
No log	0.0971	10	0.9256	0.0710	0.9256	0.9621
No log	0.1165	12	0.9407	0.1116	0.9407	0.9699
No log	0.1359	14	0.8663	0.1851	0.8663	0.9308
No log	0.1553	16	0.8053	0.1939	0.8053	0.8974
No log	0.1748	18	0.8264	0.2969	0.8264	0.9091
No log	0.1942	20	0.7996	0.3128	0.7996	0.8942
No log	0.2136	22	0.7672	0.3070	0.7672	0.8759
No log	0.2330	24	0.7423	0.3493	0.7423	0.8615
No log	0.2524	26	0.7053	0.3773	0.7053	0.8398
No log	0.2718	28	0.6931	0.4285	0.6931	0.8325
No log	0.2913	30	0.6954	0.4323	0.6954	0.8339
No log	0.3107	32	0.6209	0.5082	0.6209	0.7880
No log	0.3301	34	0.6336	0.5154	0.6336	0.7960
No log	0.3495	36	0.6071	0.5417	0.6071	0.7792
No log	0.3689	38	0.6171	0.5560	0.6171	0.7856
No log	0.3883	40	0.6871	0.5063	0.6871	0.8289
No log	0.4078	42	0.6788	0.5518	0.6788	0.8239
No log	0.4272	44	0.5825	0.5694	0.5825	0.7632
No log	0.4466	46	0.5647	0.5919	0.5647	0.7515
No log	0.4660	48	0.5922	0.5468	0.5922	0.7695
No log	0.4854	50	0.8638	0.5181	0.8638	0.9294
No log	0.5049	52	0.9877	0.4587	0.9877	0.9938
No log	0.5243	54	0.7382	0.5530	0.7382	0.8592
No log	0.5437	56	0.5330	0.6057	0.5330	0.7301
No log	0.5631	58	0.6112	0.5057	0.6112	0.7818
No log	0.5825	60	0.7426	0.3704	0.7426	0.8617
No log	0.6019	62	0.6928	0.3671	0.6928	0.8323
No log	0.6214	64	0.6037	0.4514	0.6037	0.7770
No log	0.6408	66	0.5612	0.5421	0.5612	0.7491
No log	0.6602	68	0.5471	0.5701	0.5471	0.7396
No log	0.6796	70	0.5725	0.4782	0.5725	0.7566
No log	0.6990	72	0.5697	0.4861	0.5697	0.7548
No log	0.7184	74	0.5511	0.5503	0.5511	0.7424
No log	0.7379	76	0.6017	0.5792	0.6017	0.7757
No log	0.7573	78	0.5777	0.6096	0.5777	0.7601
No log	0.7767	80	0.5417	0.6301	0.5417	0.7360
No log	0.7961	82	0.5257	0.6334	0.5257	0.7250
No log	0.8155	84	0.5012	0.6310	0.5012	0.7079
No log	0.8350	86	0.4976	0.6246	0.4976	0.7054
No log	0.8544	88	0.4977	0.6193	0.4977	0.7055
No log	0.8738	90	0.5202	0.6239	0.5202	0.7212
No log	0.8932	92	0.5454	0.6332	0.5454	0.7385
No log	0.9126	94	0.5883	0.6282	0.5883	0.7670
No log	0.9320	96	0.5793	0.6322	0.5793	0.7611
No log	0.9515	98	0.5216	0.6243	0.5216	0.7222
No log	0.9709	100	0.5022	0.5369	0.5022	0.7086
No log	0.9903	102	0.6015	0.5407	0.6015	0.7756
No log	1.0097	104	0.6073	0.5271	0.6073	0.7793
No log	1.0291	106	0.5453	0.4956	0.5453	0.7384
No log	1.0485	108	0.5027	0.5272	0.5027	0.7090
No log	1.0680	110	0.5162	0.6383	0.5162	0.7185
No log	1.0874	112	0.5018	0.6401	0.5018	0.7084
No log	1.1068	114	0.4678	0.6687	0.4678	0.6839
No log	1.1262	116	0.5719	0.6737	0.5719	0.7562
No log	1.1456	118	0.6392	0.6595	0.6392	0.7995
No log	1.1650	120	0.5110	0.6874	0.5110	0.7148
No log	1.1845	122	0.4518	0.6910	0.4518	0.6722
No log	1.2039	124	0.5736	0.6334	0.5736	0.7574
No log	1.2233	126	0.7401	0.5260	0.7401	0.8603
No log	1.2427	128	0.7479	0.4511	0.7479	0.8648
No log	1.2621	130	0.6988	0.4070	0.6988	0.8360
No log	1.2816	132	0.6364	0.5184	0.6364	0.7978
No log	1.3010	134	0.6632	0.5312	0.6632	0.8144
No log	1.3204	136	0.6888	0.5408	0.6888	0.8299
No log	1.3398	138	0.7346	0.5499	0.7346	0.8571
No log	1.3592	140	0.5580	0.6149	0.5580	0.7470
No log	1.3786	142	0.4819	0.5670	0.4819	0.6942
No log	1.3981	144	0.4842	0.5933	0.4842	0.6958
No log	1.4175	146	0.4877	0.6253	0.4877	0.6984
No log	1.4369	148	0.4455	0.6811	0.4455	0.6674
No log	1.4563	150	0.4991	0.6746	0.4991	0.7065
No log	1.4757	152	0.5378	0.6631	0.5378	0.7333
No log	1.4951	154	0.5041	0.6624	0.5041	0.7100
No log	1.5146	156	0.5315	0.6538	0.5315	0.7290
No log	1.5340	158	0.8432	0.5746	0.8432	0.9183
No log	1.5534	160	0.9750	0.5291	0.9750	0.9874
No log	1.5728	162	0.8029	0.5764	0.8029	0.8960
No log	1.5922	164	0.5667	0.6145	0.5667	0.7528
No log	1.6117	166	0.4620	0.6285	0.4620	0.6797
No log	1.6311	168	0.4502	0.6411	0.4502	0.6710
No log	1.6505	170	0.4514	0.6537	0.4514	0.6718
No log	1.6699	172	0.5017	0.6646	0.5017	0.7083
No log	1.6893	174	0.4956	0.6543	0.4956	0.7040
No log	1.7087	176	0.5726	0.6613	0.5726	0.7567
No log	1.7282	178	0.5427	0.6668	0.5427	0.7367
No log	1.7476	180	0.4456	0.6179	0.4456	0.6675
No log	1.7670	182	0.4521	0.6308	0.4521	0.6724
No log	1.7864	184	0.4376	0.6492	0.4376	0.6615
No log	1.8058	186	0.4791	0.6844	0.4791	0.6922
No log	1.8252	188	0.4932	0.6869	0.4932	0.7023
No log	1.8447	190	0.4504	0.7032	0.4504	0.6711
No log	1.8641	192	0.4387	0.6782	0.4387	0.6623
No log	1.8835	194	0.4527	0.6805	0.4527	0.6728
No log	1.9029	196	0.4341	0.7007	0.4341	0.6589
No log	1.9223	198	0.4334	0.7079	0.4334	0.6584
No log	1.9417	200	0.4344	0.6754	0.4344	0.6591
No log	1.9612	202	0.4820	0.6238	0.4820	0.6943
No log	1.9806	204	0.6403	0.5502	0.6403	0.8002
No log	2.0	206	0.7482	0.5094	0.7482	0.8650
No log	2.0194	208	0.6766	0.5351	0.6766	0.8226
No log	2.0388	210	0.5399	0.5662	0.5399	0.7348
No log	2.0583	212	0.4729	0.6033	0.4729	0.6877
No log	2.0777	214	0.4753	0.6498	0.4753	0.6894
No log	2.0971	216	0.4935	0.6812	0.4935	0.7025
No log	2.1165	218	0.4484	0.6921	0.4484	0.6696
No log	2.1359	220	0.4512	0.7137	0.4512	0.6717
No log	2.1553	222	0.4981	0.6833	0.4981	0.7058
No log	2.1748	224	0.4509	0.7280	0.4509	0.6715
No log	2.1942	226	0.4422	0.6828	0.4422	0.6650
No log	2.2136	228	0.4465	0.6921	0.4465	0.6682
No log	2.2330	230	0.4568	0.7052	0.4568	0.6759
No log	2.2524	232	0.4713	0.7026	0.4713	0.6865
No log	2.2718	234	0.4380	0.7073	0.4380	0.6618
No log	2.2913	236	0.4423	0.6995	0.4423	0.6651
No log	2.3107	238	0.5015	0.6832	0.5015	0.7082
No log	2.3301	240	0.4571	0.7076	0.4571	0.6761
No log	2.3495	242	0.4426	0.7089	0.4426	0.6653
No log	2.3689	244	0.5016	0.6710	0.5016	0.7083
No log	2.3883	246	0.5221	0.6646	0.5221	0.7225
No log	2.4078	248	0.4532	0.6910	0.4532	0.6732
No log	2.4272	250	0.4721	0.6533	0.4721	0.6871
No log	2.4466	252	0.6486	0.5666	0.6486	0.8054
No log	2.4660	254	0.7267	0.5592	0.7267	0.8525
No log	2.4854	256	0.6393	0.5366	0.6393	0.7996
No log	2.5049	258	0.5174	0.5748	0.5174	0.7193
No log	2.5243	260	0.4680	0.5898	0.4680	0.6841
No log	2.5437	262	0.4921	0.6295	0.4921	0.7015
No log	2.5631	264	0.4745	0.6493	0.4745	0.6889
No log	2.5825	266	0.5415	0.6504	0.5415	0.7359
No log	2.6019	268	0.7579	0.5523	0.7579	0.8706
No log	2.6214	270	0.6364	0.5884	0.6364	0.7977
No log	2.6408	272	0.4756	0.6946	0.4756	0.6896
No log	2.6602	274	0.6544	0.6441	0.6544	0.8089
No log	2.6796	276	0.6753	0.6463	0.6753	0.8218
No log	2.6990	278	0.5889	0.6859	0.5889	0.7674
No log	2.7184	280	0.5004	0.6511	0.5004	0.7074
No log	2.7379	282	0.4758	0.6684	0.4758	0.6897
No log	2.7573	284	0.4707	0.6658	0.4707	0.6861
No log	2.7767	286	0.4598	0.6704	0.4598	0.6781
No log	2.7961	288	0.4535	0.6700	0.4535	0.6734
No log	2.8155	290	0.4598	0.6771	0.4598	0.6781
No log	2.8350	292	0.4619	0.6816	0.4619	0.6796
No log	2.8544	294	0.4753	0.6952	0.4753	0.6895
No log	2.8738	296	0.5110	0.7294	0.5110	0.7148
No log	2.8932	298	0.5886	0.7283	0.5886	0.7672
No log	2.9126	300	0.6281	0.6810	0.6281	0.7925
No log	2.9320	302	0.5759	0.6927	0.5759	0.7589
No log	2.9515	304	0.5321	0.6928	0.5321	0.7295
No log	2.9709	306	0.4946	0.6939	0.4946	0.7033
No log	2.9903	308	0.4623	0.6665	0.4623	0.6799
No log	3.0097	310	0.4413	0.6529	0.4413	0.6643
No log	3.0291	312	0.4423	0.6564	0.4423	0.6650
No log	3.0485	314	0.4552	0.6402	0.4552	0.6747
No log	3.0680	316	0.4748	0.6249	0.4748	0.6890
No log	3.0874	318	0.4493	0.6587	0.4493	0.6703
No log	3.1068	320	0.4759	0.6797	0.4759	0.6899
No log	3.1262	322	0.6334	0.6429	0.6334	0.7959
No log	3.1456	324	0.6790	0.6251	0.6790	0.8240
No log	3.1650	326	0.5726	0.6531	0.5726	0.7567
No log	3.1845	328	0.4479	0.6946	0.4479	0.6693
No log	3.2039	330	0.4758	0.6608	0.4758	0.6898
No log	3.2233	332	0.6186	0.6172	0.6186	0.7865
No log	3.2427	334	0.6132	0.6076	0.6132	0.7831
No log	3.2621	336	0.4894	0.6193	0.4894	0.6995
No log	3.2816	338	0.4431	0.6353	0.4431	0.6657
No log	3.3010	340	0.5654	0.6369	0.5654	0.7520
No log	3.3204	342	0.6348	0.6453	0.6348	0.7967
No log	3.3398	344	0.5883	0.6557	0.5883	0.7670
No log	3.3592	346	0.4703	0.6463	0.4703	0.6858
No log	3.3786	348	0.4393	0.6828	0.4393	0.6628
No log	3.3981	350	0.4852	0.6869	0.4852	0.6966
No log	3.4175	352	0.5126	0.6638	0.5126	0.7159
No log	3.4369	354	0.5311	0.6397	0.5311	0.7287
No log	3.4563	356	0.5566	0.6511	0.5566	0.7461
No log	3.4757	358	0.5242	0.6643	0.5242	0.7240
No log	3.4951	360	0.4942	0.6423	0.4942	0.7030
No log	3.5146	362	0.4559	0.6490	0.4559	0.6752
No log	3.5340	364	0.4363	0.6517	0.4363	0.6605
No log	3.5534	366	0.4395	0.6276	0.4395	0.6629
No log	3.5728	368	0.4524	0.6144	0.4524	0.6726
No log	3.5922	370	0.4660	0.5916	0.4660	0.6826
No log	3.6117	372	0.4527	0.6080	0.4527	0.6729
No log	3.6311	374	0.4321	0.6594	0.4321	0.6574
No log	3.6505	376	0.4373	0.7015	0.4373	0.6613
No log	3.6699	378	0.4596	0.7031	0.4596	0.6779
No log	3.6893	380	0.4920	0.7384	0.4920	0.7014
No log	3.7087	382	0.4819	0.7333	0.4819	0.6942
No log	3.7282	384	0.4468	0.7142	0.4468	0.6684
No log	3.7476	386	0.4363	0.7110	0.4363	0.6606
No log	3.7670	388	0.4644	0.6779	0.4644	0.6814
No log	3.7864	390	0.6443	0.5920	0.6443	0.8027
No log	3.8058	392	0.7543	0.5308	0.7543	0.8685
No log	3.8252	394	0.6539	0.5566	0.6539	0.8086
No log	3.8447	396	0.5486	0.6128	0.5486	0.7406
No log	3.8641	398	0.4718	0.6205	0.4718	0.6869
No log	3.8835	400	0.4829	0.6177	0.4829	0.6949
No log	3.9029	402	0.4548	0.6646	0.4548	0.6744
No log	3.9223	404	0.4366	0.6724	0.4366	0.6607
No log	3.9417	406	0.5033	0.6967	0.5033	0.7095
No log	3.9612	408	0.4971	0.6966	0.4971	0.7051
No log	3.9806	410	0.4849	0.7252	0.4849	0.6964
No log	4.0	412	0.4537	0.7171	0.4537	0.6736
No log	4.0194	414	0.4608	0.7148	0.4608	0.6788
No log	4.0388	416	0.4373	0.7196	0.4373	0.6613
No log	4.0583	418	0.4400	0.6962	0.4400	0.6633
No log	4.0777	420	0.4351	0.7043	0.4351	0.6596
No log	4.0971	422	0.4215	0.6971	0.4215	0.6492
No log	4.1165	424	0.4488	0.6892	0.4488	0.6699
No log	4.1359	426	0.4257	0.6739	0.4257	0.6524
No log	4.1553	428	0.4830	0.6629	0.4830	0.6949
No log	4.1748	430	0.5567	0.6497	0.5567	0.7461
No log	4.1942	432	0.5436	0.6922	0.5436	0.7373
No log	4.2136	434	0.4617	0.7004	0.4617	0.6795
No log	4.2330	436	0.4309	0.7176	0.4309	0.6564
No log	4.2524	438	0.4357	0.7464	0.4357	0.6601
No log	4.2718	440	0.4719	0.7410	0.4719	0.6869
No log	4.2913	442	0.6162	0.6809	0.6162	0.7850
No log	4.3107	444	0.5812	0.6872	0.5812	0.7624
No log	4.3301	446	0.4493	0.7030	0.4493	0.6703
No log	4.3495	448	0.4252	0.6785	0.4252	0.6521
No log	4.3689	450	0.4876	0.6191	0.4876	0.6983
No log	4.3883	452	0.4719	0.6192	0.4719	0.6869
No log	4.4078	454	0.4536	0.6234	0.4536	0.6735
No log	4.4272	456	0.4521	0.6246	0.4521	0.6724
No log	4.4466	458	0.4544	0.6726	0.4544	0.6741
No log	4.4660	460	0.5109	0.6737	0.5109	0.7147
No log	4.4854	462	0.4862	0.6985	0.4862	0.6973
No log	4.5049	464	0.4656	0.7203	0.4656	0.6824
No log	4.5243	466	0.5105	0.6985	0.5105	0.7145
No log	4.5437	468	0.5725	0.6689	0.5725	0.7566
No log	4.5631	470	0.5264	0.6979	0.5264	0.7255
No log	4.5825	472	0.5143	0.7240	0.5143	0.7172
No log	4.6019	474	0.5417	0.6965	0.5417	0.7360
No log	4.6214	476	0.5395	0.6831	0.5395	0.7345
No log	4.6408	478	0.4970	0.6756	0.4970	0.7049
No log	4.6602	480	0.4897	0.6814	0.4897	0.6998
No log	4.6796	482	0.4669	0.6759	0.4669	0.6833
No log	4.6990	484	0.4537	0.7009	0.4537	0.6736
No log	4.7184	486	0.4829	0.7341	0.4829	0.6949
No log	4.7379	488	0.5553	0.7076	0.5553	0.7452
No log	4.7573	490	0.5574	0.7205	0.5574	0.7466
No log	4.7767	492	0.5143	0.7137	0.5143	0.7171
No log	4.7961	494	0.4803	0.7105	0.4803	0.6930
No log	4.8155	496	0.4504	0.7153	0.4504	0.6711
No log	4.8350	498	0.4429	0.7014	0.4429	0.6655
0.5147	4.8544	500	0.4354	0.6832	0.4354	0.6598
0.5147	4.8738	502	0.4604	0.6595	0.4604	0.6785
0.5147	4.8932	504	0.4565	0.6583	0.4565	0.6756
0.5147	4.9126	506	0.4307	0.6805	0.4307	0.6563
0.5147	4.9320	508	0.4725	0.6711	0.4725	0.6874
0.5147	4.9515	510	0.5136	0.6644	0.5136	0.7166

Framework versions

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