Arabic_CrossPrompt_FineTuningAraBERT_noAug_TestTask6_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: 0.5043
• Qwk: 0.5939
• Mse: 0.5043
• Rmse: 0.7101

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	5.0185	-0.0129	5.0185	2.2402
No log	0.0388	4	2.9396	0.0340	2.9396	1.7145
No log	0.0583	6	1.5723	0.0107	1.5723	1.2539
No log	0.0777	8	1.0046	0.1951	1.0046	1.0023
No log	0.0971	10	0.9021	0.2164	0.9021	0.9498
No log	0.1165	12	0.7757	0.2351	0.7757	0.8808
No log	0.1359	14	0.8886	0.2783	0.8886	0.9427
No log	0.1553	16	0.8244	0.3383	0.8244	0.9080
No log	0.1748	18	0.6587	0.4086	0.6587	0.8116
No log	0.1942	20	1.4258	0.2606	1.4258	1.1941
No log	0.2136	22	1.6812	0.2299	1.6812	1.2966
No log	0.2330	24	1.1817	0.2976	1.1817	1.0870
No log	0.2524	26	0.6237	0.4497	0.6237	0.7898
No log	0.2718	28	0.7439	0.3684	0.7439	0.8625
No log	0.2913	30	0.8713	0.1200	0.8713	0.9334
No log	0.3107	32	0.8233	0.1393	0.8233	0.9073
No log	0.3301	34	0.6951	0.2541	0.6951	0.8337
No log	0.3495	36	0.6489	0.3517	0.6489	0.8055
No log	0.3689	38	0.6482	0.3727	0.6482	0.8051
No log	0.3883	40	0.6171	0.4117	0.6171	0.7855
No log	0.4078	42	0.6288	0.5058	0.6288	0.7929
No log	0.4272	44	0.6472	0.5511	0.6472	0.8045
No log	0.4466	46	0.6464	0.5574	0.6464	0.8040
No log	0.4660	48	0.6805	0.5896	0.6805	0.8249
No log	0.4854	50	0.6914	0.6018	0.6914	0.8315
No log	0.5049	52	0.6490	0.5776	0.6490	0.8056
No log	0.5243	54	0.6433	0.5199	0.6433	0.8021
No log	0.5437	56	0.8356	0.4986	0.8356	0.9141
No log	0.5631	58	0.9066	0.4738	0.9066	0.9522
No log	0.5825	60	0.7273	0.5117	0.7273	0.8528
No log	0.6019	62	0.5856	0.5143	0.5856	0.7653
No log	0.6214	64	0.5471	0.4574	0.5471	0.7397
No log	0.6408	66	0.5823	0.4981	0.5823	0.7631
No log	0.6602	68	0.6212	0.4906	0.6212	0.7882
No log	0.6796	70	0.5922	0.5154	0.5922	0.7695
No log	0.6990	72	0.5612	0.5341	0.5612	0.7491
No log	0.7184	74	0.5135	0.4796	0.5135	0.7166
No log	0.7379	76	0.5082	0.4922	0.5082	0.7129
No log	0.7573	78	0.5285	0.4901	0.5285	0.7270
No log	0.7767	80	0.6103	0.5209	0.6103	0.7812
No log	0.7961	82	0.6812	0.4771	0.6812	0.8254
No log	0.8155	84	0.6926	0.4647	0.6926	0.8322
No log	0.8350	86	0.5713	0.4938	0.5713	0.7558
No log	0.8544	88	0.5054	0.5667	0.5054	0.7109
No log	0.8738	90	0.5707	0.5959	0.5707	0.7554
No log	0.8932	92	0.6008	0.6130	0.6008	0.7751
No log	0.9126	94	0.5892	0.6104	0.5892	0.7676
No log	0.9320	96	0.6716	0.5943	0.6716	0.8195
No log	0.9515	98	0.7515	0.5650	0.7515	0.8669
No log	0.9709	100	0.6382	0.6054	0.6382	0.7989
No log	0.9903	102	0.5340	0.6517	0.5340	0.7307
No log	1.0097	104	0.5589	0.6064	0.5589	0.7476
No log	1.0291	106	0.5618	0.6024	0.5618	0.7495
No log	1.0485	108	0.5105	0.6228	0.5105	0.7145
No log	1.0680	110	0.4902	0.6028	0.4902	0.7001
No log	1.0874	112	0.4895	0.5383	0.4895	0.6996
No log	1.1068	114	0.4925	0.5240	0.4925	0.7018
No log	1.1262	116	0.4858	0.5276	0.4858	0.6970
No log	1.1456	118	0.4933	0.5846	0.4933	0.7024
No log	1.1650	120	0.5781	0.5478	0.5781	0.7603
No log	1.1845	122	0.6169	0.5625	0.6169	0.7854
No log	1.2039	124	0.5393	0.5795	0.5393	0.7344
No log	1.2233	126	0.4967	0.5583	0.4967	0.7048
No log	1.2427	128	0.4764	0.5533	0.4764	0.6902
No log	1.2621	130	0.4815	0.4923	0.4815	0.6939
No log	1.2816	132	0.4704	0.5279	0.4704	0.6858
No log	1.3010	134	0.4655	0.5905	0.4655	0.6823
No log	1.3204	136	0.5077	0.6196	0.5077	0.7126
No log	1.3398	138	0.5011	0.6468	0.5011	0.7079
No log	1.3592	140	0.5052	0.6685	0.5052	0.7108
No log	1.3786	142	0.6131	0.5736	0.6131	0.7830
No log	1.3981	144	0.6537	0.5500	0.6537	0.8085
No log	1.4175	146	0.5958	0.5884	0.5958	0.7719
No log	1.4369	148	0.5857	0.5966	0.5857	0.7653
No log	1.4563	150	0.5901	0.5407	0.5901	0.7682
No log	1.4757	152	0.5959	0.5280	0.5959	0.7720
No log	1.4951	154	0.5597	0.5043	0.5597	0.7481
No log	1.5146	156	0.5805	0.5259	0.5805	0.7619
No log	1.5340	158	0.6225	0.5301	0.6225	0.7890
No log	1.5534	160	0.6014	0.5343	0.6014	0.7755
No log	1.5728	162	0.5468	0.5466	0.5468	0.7394
No log	1.5922	164	0.5146	0.5381	0.5146	0.7174
No log	1.6117	166	0.5428	0.5822	0.5428	0.7367
No log	1.6311	168	0.5028	0.5799	0.5028	0.7091
No log	1.6505	170	0.4712	0.6016	0.4712	0.6864
No log	1.6699	172	0.5099	0.5266	0.5099	0.7141
No log	1.6893	174	0.4636	0.5760	0.4636	0.6809
No log	1.7087	176	0.4573	0.6305	0.4573	0.6763
No log	1.7282	178	0.5367	0.5659	0.5367	0.7326
No log	1.7476	180	0.5682	0.5761	0.5682	0.7538
No log	1.7670	182	0.5302	0.5743	0.5302	0.7282
No log	1.7864	184	0.4951	0.5980	0.4951	0.7036
No log	1.8058	186	0.4841	0.5819	0.4841	0.6958
No log	1.8252	188	0.5124	0.6044	0.5124	0.7158
No log	1.8447	190	0.5255	0.6160	0.5255	0.7249
No log	1.8641	192	0.4934	0.6026	0.4934	0.7024
No log	1.8835	194	0.4855	0.6246	0.4855	0.6968
No log	1.9029	196	0.4680	0.6270	0.4680	0.6841
No log	1.9223	198	0.4763	0.6507	0.4763	0.6901
No log	1.9417	200	0.4737	0.6590	0.4737	0.6882
No log	1.9612	202	0.5355	0.6248	0.5355	0.7318
No log	1.9806	204	0.5802	0.6199	0.5802	0.7617
No log	2.0	206	0.5328	0.6052	0.5328	0.7300
No log	2.0194	208	0.5278	0.6075	0.5278	0.7265
No log	2.0388	210	0.5362	0.6045	0.5362	0.7323
No log	2.0583	212	0.5709	0.6156	0.5709	0.7556
No log	2.0777	214	0.5900	0.6204	0.5900	0.7681
No log	2.0971	216	0.5552	0.6250	0.5552	0.7451
No log	2.1165	218	0.5440	0.5994	0.5440	0.7376
No log	2.1359	220	0.5055	0.6177	0.5055	0.7110
No log	2.1553	222	0.5128	0.6063	0.5128	0.7161
No log	2.1748	224	0.5069	0.6026	0.5069	0.7120
No log	2.1942	226	0.4857	0.6086	0.4857	0.6969
No log	2.2136	228	0.5261	0.6406	0.5261	0.7253
No log	2.2330	230	0.6282	0.5701	0.6282	0.7926
No log	2.2524	232	0.6307	0.5805	0.6307	0.7941
No log	2.2718	234	0.5401	0.6312	0.5401	0.7349
No log	2.2913	236	0.6096	0.6168	0.6096	0.7808
No log	2.3107	238	0.6558	0.6171	0.6558	0.8098
No log	2.3301	240	0.6020	0.6242	0.6020	0.7759
No log	2.3495	242	0.5460	0.6191	0.5460	0.7389
No log	2.3689	244	0.5831	0.5926	0.5831	0.7636
No log	2.3883	246	0.5659	0.5819	0.5659	0.7522
No log	2.4078	248	0.4981	0.5535	0.4981	0.7058
No log	2.4272	250	0.4630	0.5618	0.4630	0.6804
No log	2.4466	252	0.4554	0.5702	0.4554	0.6748
No log	2.4660	254	0.4838	0.5997	0.4838	0.6956
No log	2.4854	256	0.5475	0.6177	0.5475	0.7399
No log	2.5049	258	0.5324	0.6314	0.5324	0.7297
No log	2.5243	260	0.5035	0.6247	0.5035	0.7096
No log	2.5437	262	0.4603	0.6489	0.4603	0.6785
No log	2.5631	264	0.5295	0.6174	0.5295	0.7277
No log	2.5825	266	0.6091	0.6155	0.6091	0.7804
No log	2.6019	268	0.5501	0.6144	0.5501	0.7417
No log	2.6214	270	0.4845	0.6304	0.4845	0.6960
No log	2.6408	272	0.5389	0.6153	0.5389	0.7341
No log	2.6602	274	0.5236	0.6159	0.5236	0.7236
No log	2.6796	276	0.4803	0.6255	0.4803	0.6931
No log	2.6990	278	0.4717	0.6234	0.4717	0.6868
No log	2.7184	280	0.4631	0.6131	0.4631	0.6805
No log	2.7379	282	0.4621	0.5859	0.4621	0.6798
No log	2.7573	284	0.4714	0.6284	0.4714	0.6866
No log	2.7767	286	0.5291	0.6261	0.5291	0.7274
No log	2.7961	288	0.5714	0.6298	0.5714	0.7559
No log	2.8155	290	0.7010	0.6097	0.7010	0.8373
No log	2.8350	292	0.7396	0.6030	0.7396	0.8600
No log	2.8544	294	0.6527	0.6545	0.6527	0.8079
No log	2.8738	296	0.5766	0.6537	0.5766	0.7593
No log	2.8932	298	0.5636	0.6490	0.5636	0.7507
No log	2.9126	300	0.5956	0.6145	0.5956	0.7718
No log	2.9320	302	0.5988	0.5997	0.5988	0.7738
No log	2.9515	304	0.5256	0.6304	0.5256	0.7250
No log	2.9709	306	0.4523	0.6053	0.4523	0.6725
No log	2.9903	308	0.5132	0.5035	0.5132	0.7164
No log	3.0097	310	0.5535	0.4775	0.5535	0.7440
No log	3.0291	312	0.5141	0.5125	0.5141	0.7170
No log	3.0485	314	0.4796	0.5615	0.4796	0.6926
No log	3.0680	316	0.4711	0.6260	0.4711	0.6864
No log	3.0874	318	0.4764	0.6556	0.4764	0.6902
No log	3.1068	320	0.5471	0.6321	0.5471	0.7397
No log	3.1262	322	0.6458	0.6169	0.6458	0.8036
No log	3.1456	324	0.6997	0.5904	0.6997	0.8365
No log	3.1650	326	0.6804	0.5835	0.6804	0.8249
No log	3.1845	328	0.6154	0.6293	0.6154	0.7845
No log	3.2039	330	0.5867	0.6604	0.5867	0.7660
No log	3.2233	332	0.7011	0.5611	0.7011	0.8373
No log	3.2427	334	0.6714	0.6000	0.6714	0.8194
No log	3.2621	336	0.4959	0.6034	0.4959	0.7042
No log	3.2816	338	0.4689	0.5524	0.4689	0.6847
No log	3.3010	340	0.4901	0.5342	0.4901	0.7001
No log	3.3204	342	0.5012	0.5062	0.5012	0.7079
No log	3.3398	344	0.4821	0.5312	0.4821	0.6943
No log	3.3592	346	0.4882	0.5679	0.4882	0.6987
No log	3.3786	348	0.5437	0.6194	0.5437	0.7373
No log	3.3981	350	0.5610	0.5985	0.5610	0.7490
No log	3.4175	352	0.5199	0.6184	0.5199	0.7210
No log	3.4369	354	0.5316	0.6360	0.5316	0.7291
No log	3.4563	356	0.5564	0.6345	0.5564	0.7459
No log	3.4757	358	0.5545	0.6239	0.5545	0.7446
No log	3.4951	360	0.5846	0.5769	0.5846	0.7646
No log	3.5146	362	0.5746	0.5745	0.5746	0.7581
No log	3.5340	364	0.5257	0.6184	0.5257	0.7250
No log	3.5534	366	0.5324	0.6134	0.5324	0.7296
No log	3.5728	368	0.5801	0.5772	0.5801	0.7617
No log	3.5922	370	0.5960	0.5785	0.5960	0.7720
No log	3.6117	372	0.6188	0.5673	0.6188	0.7867
No log	3.6311	374	0.5733	0.6112	0.5733	0.7572
No log	3.6505	376	0.5183	0.6426	0.5183	0.7199
No log	3.6699	378	0.5238	0.6428	0.5238	0.7237
No log	3.6893	380	0.6038	0.6206	0.6038	0.7770
No log	3.7087	382	0.7103	0.6014	0.7103	0.8428
No log	3.7282	384	0.7364	0.5703	0.7364	0.8581
No log	3.7476	386	0.6206	0.6061	0.6206	0.7878
No log	3.7670	388	0.4774	0.6403	0.4774	0.6910
No log	3.7864	390	0.4610	0.6240	0.4610	0.6789
No log	3.8058	392	0.5178	0.6357	0.5178	0.7196
No log	3.8252	394	0.4679	0.6367	0.4679	0.6841
No log	3.8447	396	0.4468	0.6088	0.4468	0.6685
No log	3.8641	398	0.4443	0.6414	0.4443	0.6665
No log	3.8835	400	0.4607	0.6664	0.4607	0.6788
No log	3.9029	402	0.4886	0.6733	0.4886	0.6990
No log	3.9223	404	0.4933	0.6665	0.4933	0.7023
No log	3.9417	406	0.6363	0.6004	0.6363	0.7977
No log	3.9612	408	0.5993	0.5946	0.5993	0.7741
No log	3.9806	410	0.4883	0.6469	0.4883	0.6988
No log	4.0	412	0.4980	0.6455	0.4980	0.7057
No log	4.0194	414	0.4722	0.6336	0.4722	0.6872
No log	4.0388	416	0.4709	0.6563	0.4709	0.6862
No log	4.0583	418	0.6482	0.5841	0.6482	0.8051
No log	4.0777	420	0.6921	0.5807	0.6921	0.8319
No log	4.0971	422	0.5601	0.6277	0.5601	0.7484
No log	4.1165	424	0.5036	0.6443	0.5036	0.7096
No log	4.1359	426	0.5252	0.6293	0.5252	0.7247
No log	4.1553	428	0.4969	0.6802	0.4969	0.7049
No log	4.1748	430	0.6433	0.6113	0.6433	0.8021
No log	4.1942	432	0.8000	0.5576	0.8000	0.8945
No log	4.2136	434	0.7291	0.5501	0.7291	0.8539
No log	4.2330	436	0.5664	0.6039	0.5664	0.7526
No log	4.2524	438	0.5335	0.6424	0.5335	0.7304
No log	4.2718	440	0.5453	0.6374	0.5453	0.7384
No log	4.2913	442	0.6212	0.5766	0.6212	0.7882
No log	4.3107	444	0.6525	0.5626	0.6525	0.8077
No log	4.3301	446	0.5421	0.6317	0.5421	0.7363
No log	4.3495	448	0.4732	0.6086	0.4732	0.6879
No log	4.3689	450	0.4728	0.6159	0.4728	0.6876
No log	4.3883	452	0.5124	0.6399	0.5124	0.7158
No log	4.4078	454	0.6048	0.6269	0.6048	0.7777
No log	4.4272	456	0.6392	0.6105	0.6392	0.7995
No log	4.4466	458	0.5977	0.6313	0.5977	0.7731
No log	4.4660	460	0.5276	0.6374	0.5276	0.7263
No log	4.4854	462	0.5003	0.6576	0.5003	0.7073
No log	4.5049	464	0.5031	0.6160	0.5031	0.7093
No log	4.5243	466	0.5266	0.6264	0.5266	0.7257
No log	4.5437	468	0.5167	0.6555	0.5167	0.7188
No log	4.5631	470	0.6057	0.6372	0.6057	0.7782
No log	4.5825	472	0.6771	0.6296	0.6771	0.8229
No log	4.6019	474	0.6840	0.6126	0.6840	0.8270
No log	4.6214	476	0.6895	0.6180	0.6895	0.8304
No log	4.6408	478	0.7669	0.5934	0.7669	0.8757
No log	4.6602	480	0.6391	0.6565	0.6391	0.7995
No log	4.6796	482	0.5674	0.6751	0.5674	0.7533
No log	4.6990	484	0.5409	0.6634	0.5409	0.7354
No log	4.7184	486	0.4929	0.6493	0.4929	0.7021
No log	4.7379	488	0.4682	0.6264	0.4682	0.6842
No log	4.7573	490	0.4998	0.6629	0.4998	0.7070
No log	4.7767	492	0.6387	0.5938	0.6387	0.7992
No log	4.7961	494	0.5536	0.6225	0.5536	0.7441
No log	4.8155	496	0.4551	0.6336	0.4551	0.6746
No log	4.8350	498	0.4391	0.6238	0.4391	0.6627
0.527	4.8544	500	0.4298	0.6166	0.4298	0.6556
0.527	4.8738	502	0.4278	0.6371	0.4278	0.6541
0.527	4.8932	504	0.4767	0.6567	0.4767	0.6904
0.527	4.9126	506	0.5171	0.6740	0.5171	0.7191
0.527	4.9320	508	0.4616	0.6911	0.4616	0.6794
0.527	4.9515	510	0.4704	0.6924	0.4704	0.6858
0.527	4.9709	512	0.5043	0.6835	0.5043	0.7101
0.527	4.9903	514	0.6404	0.6730	0.6404	0.8002
0.527	5.0097	516	0.7511	0.6016	0.7511	0.8667
0.527	5.0291	518	0.6328	0.6483	0.6328	0.7955
0.527	5.0485	520	0.4811	0.6617	0.4811	0.6936
0.527	5.0680	522	0.4744	0.6629	0.4744	0.6888
0.527	5.0874	524	0.5357	0.6442	0.5357	0.7319
0.527	5.1068	526	0.5974	0.6478	0.5974	0.7729
0.527	5.1262	528	0.6125	0.6468	0.6125	0.7826
0.527	5.1456	530	0.6401	0.6256	0.6401	0.8001
0.527	5.1650	532	0.6535	0.6226	0.6535	0.8084
0.527	5.1845	534	0.5774	0.6423	0.5774	0.7599
0.527	5.2039	536	0.5787	0.6433	0.5787	0.7607
0.527	5.2233	538	0.5225	0.6435	0.5225	0.7229
0.527	5.2427	540	0.4607	0.6228	0.4607	0.6787
0.527	5.2621	542	0.4653	0.5769	0.4653	0.6821
0.527	5.2816	544	0.4786	0.6189	0.4786	0.6918
0.527	5.3010	546	0.6743	0.5974	0.6743	0.8212
0.527	5.3204	548	0.9360	0.4811	0.9360	0.9675
0.527	5.3398	550	0.9418	0.4952	0.9418	0.9705
0.527	5.3592	552	0.6920	0.5479	0.6920	0.8319
0.527	5.3786	554	0.5043	0.5939	0.5043	0.7101

Framework versions

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