Arabic_CrossPrompt_FineTuningAraBERT_noAug_TestTask7_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: 0.5122
• Qwk: 0.6327
• Mse: 0.5122
• Rmse: 0.7157

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	0.0202	2	4.6425	-0.0016	4.6425	2.1546
No log	0.0404	4	3.5211	0.0424	3.5211	1.8765
No log	0.0606	6	2.1920	0.0890	2.1920	1.4805
No log	0.0808	8	0.9420	0.1994	0.9420	0.9705
No log	0.1010	10	0.8174	0.0527	0.8174	0.9041
No log	0.1212	12	0.9957	-0.0033	0.9957	0.9979
No log	0.1414	14	0.9415	0.0827	0.9415	0.9703
No log	0.1616	16	0.8202	0.0897	0.8202	0.9056
No log	0.1818	18	0.7362	0.1023	0.7362	0.8580
No log	0.2020	20	0.6793	0.2131	0.6793	0.8242
No log	0.2222	22	0.6568	0.2051	0.6568	0.8104
No log	0.2424	24	0.6874	0.2212	0.6874	0.8291
No log	0.2626	26	0.7505	0.2945	0.7505	0.8663
No log	0.2828	28	0.7388	0.4198	0.7388	0.8595
No log	0.3030	30	0.6675	0.4752	0.6675	0.8170
No log	0.3232	32	0.6021	0.4902	0.6021	0.7760
No log	0.3434	34	0.5672	0.5322	0.5672	0.7531
No log	0.3636	36	0.5567	0.5938	0.5567	0.7462
No log	0.3838	38	0.5716	0.5911	0.5716	0.7560
No log	0.4040	40	0.5919	0.5992	0.5919	0.7693
No log	0.4242	42	0.5984	0.5898	0.5984	0.7736
No log	0.4444	44	0.5986	0.6073	0.5986	0.7737
No log	0.4646	46	0.7060	0.5036	0.7060	0.8403
No log	0.4848	48	0.7054	0.5038	0.7054	0.8399
No log	0.5051	50	0.5853	0.5572	0.5853	0.7650
No log	0.5253	52	0.5009	0.5916	0.5009	0.7077
No log	0.5455	54	0.4653	0.6264	0.4653	0.6822
No log	0.5657	56	0.4675	0.6185	0.4675	0.6837
No log	0.5859	58	0.5101	0.5389	0.5101	0.7142
No log	0.6061	60	0.4829	0.5809	0.4829	0.6949
No log	0.6263	62	0.4443	0.5819	0.4443	0.6665
No log	0.6465	64	0.4506	0.6129	0.4506	0.6712
No log	0.6667	66	0.5041	0.6263	0.5041	0.7100
No log	0.6869	68	0.7029	0.4867	0.7029	0.8384
No log	0.7071	70	0.8082	0.4482	0.8082	0.8990
No log	0.7273	72	0.7248	0.5148	0.7248	0.8513
No log	0.7475	74	0.5613	0.5877	0.5613	0.7492
No log	0.7677	76	0.4909	0.6374	0.4909	0.7007
No log	0.7879	78	0.4660	0.6514	0.4660	0.6827
No log	0.8081	80	0.4851	0.5882	0.4851	0.6965
No log	0.8283	82	0.4962	0.5610	0.4962	0.7044
No log	0.8485	84	0.4615	0.5557	0.4615	0.6793
No log	0.8687	86	0.4440	0.5635	0.4440	0.6663
No log	0.8889	88	0.4314	0.5894	0.4314	0.6568
No log	0.9091	90	0.4190	0.5780	0.4190	0.6473
No log	0.9293	92	0.4786	0.5599	0.4786	0.6918
No log	0.9495	94	0.6113	0.5707	0.6113	0.7818
No log	0.9697	96	0.5209	0.6093	0.5209	0.7217
No log	0.9899	98	0.4775	0.6045	0.4775	0.6910
No log	1.0101	100	0.4327	0.6471	0.4327	0.6578
No log	1.0303	102	0.4660	0.6414	0.4660	0.6827
No log	1.0505	104	0.6273	0.5745	0.6273	0.7920
No log	1.0707	106	0.6881	0.5560	0.6881	0.8295
No log	1.0909	108	0.5957	0.5972	0.5957	0.7718
No log	1.1111	110	0.4659	0.6273	0.4659	0.6826
No log	1.1313	112	0.4384	0.6824	0.4384	0.6621
No log	1.1515	114	0.4231	0.6581	0.4231	0.6505
No log	1.1717	116	0.4279	0.6091	0.4279	0.6541
No log	1.1919	118	0.5012	0.6160	0.5012	0.7079
No log	1.2121	120	0.5547	0.5870	0.5547	0.7448
No log	1.2323	122	0.5423	0.5928	0.5423	0.7364
No log	1.2525	124	0.5302	0.6137	0.5302	0.7282
No log	1.2727	126	0.5858	0.5847	0.5858	0.7654
No log	1.2929	128	0.4783	0.6016	0.4783	0.6916
No log	1.3131	130	0.4545	0.5997	0.4545	0.6742
No log	1.3333	132	0.4900	0.6533	0.4900	0.7000
No log	1.3535	134	0.5569	0.6246	0.5569	0.7463
No log	1.3737	136	0.6941	0.5597	0.6941	0.8331
No log	1.3939	138	0.6269	0.5530	0.6269	0.7918
No log	1.4141	140	0.5370	0.6167	0.5370	0.7328
No log	1.4343	142	0.4683	0.6273	0.4683	0.6844
No log	1.4545	144	0.4653	0.6252	0.4653	0.6821
No log	1.4747	146	0.4532	0.6137	0.4532	0.6732
No log	1.4949	148	0.4565	0.6079	0.4565	0.6756
No log	1.5152	150	0.6492	0.5182	0.6492	0.8057
No log	1.5354	152	0.8368	0.3903	0.8368	0.9148
No log	1.5556	154	0.7759	0.4540	0.7759	0.8809
No log	1.5758	156	0.5920	0.5715	0.5920	0.7694
No log	1.5960	158	0.4664	0.5772	0.4664	0.6829
No log	1.6162	160	0.4405	0.6409	0.4405	0.6637
No log	1.6364	162	0.4782	0.6378	0.4782	0.6915
No log	1.6566	164	0.5797	0.5800	0.5797	0.7614
No log	1.6768	166	0.6372	0.5521	0.6372	0.7983
No log	1.6970	168	0.5039	0.6210	0.5039	0.7098
No log	1.7172	170	0.4606	0.6636	0.4606	0.6787
No log	1.7374	172	0.4801	0.6563	0.4801	0.6929
No log	1.7576	174	0.4554	0.6752	0.4554	0.6748
No log	1.7778	176	0.4792	0.6439	0.4792	0.6923
No log	1.7980	178	0.5210	0.6281	0.5210	0.7218
No log	1.8182	180	0.6026	0.5248	0.6026	0.7763
No log	1.8384	182	0.6646	0.4807	0.6646	0.8152
No log	1.8586	184	0.7238	0.4611	0.7238	0.8508
No log	1.8788	186	0.5563	0.5518	0.5563	0.7459
No log	1.8990	188	0.4310	0.6262	0.4310	0.6565
No log	1.9192	190	0.4659	0.6464	0.4659	0.6826
No log	1.9394	192	0.5744	0.5836	0.5744	0.7579
No log	1.9596	194	0.5957	0.5864	0.5957	0.7718
No log	1.9798	196	0.5255	0.6336	0.5255	0.7249
No log	2.0	198	0.5154	0.6167	0.5154	0.7179
No log	2.0202	200	0.5811	0.5599	0.5811	0.7623
No log	2.0404	202	0.6868	0.5241	0.6868	0.8287
No log	2.0606	204	0.6167	0.5619	0.6167	0.7853
No log	2.0808	206	0.4414	0.7001	0.4414	0.6644
No log	2.1010	208	0.4241	0.7258	0.4241	0.6512
No log	2.1212	210	0.5128	0.6553	0.5128	0.7161
No log	2.1414	212	0.7633	0.5285	0.7633	0.8736
No log	2.1616	214	0.7805	0.5364	0.7805	0.8834
No log	2.1818	216	0.6143	0.5962	0.6143	0.7838
No log	2.2020	218	0.4738	0.7078	0.4738	0.6883
No log	2.2222	220	0.4811	0.6576	0.4811	0.6936
No log	2.2424	222	0.4788	0.6576	0.4788	0.6919
No log	2.2626	224	0.5424	0.6320	0.5424	0.7364
No log	2.2828	226	0.5690	0.6031	0.5690	0.7543
No log	2.3030	228	0.5594	0.6390	0.5594	0.7480
No log	2.3232	230	0.5012	0.6828	0.5012	0.7080
No log	2.3434	232	0.4376	0.6912	0.4376	0.6615
No log	2.3636	234	0.4209	0.6885	0.4209	0.6488
No log	2.3838	236	0.4412	0.6679	0.4412	0.6642
No log	2.4040	238	0.6753	0.4904	0.6753	0.8218
No log	2.4242	240	0.8822	0.3803	0.8822	0.9393
No log	2.4444	242	0.8198	0.4415	0.8198	0.9054
No log	2.4646	244	0.7410	0.4814	0.7410	0.8608
No log	2.4848	246	0.6392	0.5406	0.6392	0.7995
No log	2.5051	248	0.4713	0.6135	0.4713	0.6865
No log	2.5253	250	0.4495	0.6600	0.4495	0.6704
No log	2.5455	252	0.4332	0.6803	0.4332	0.6582
No log	2.5657	254	0.4518	0.6980	0.4518	0.6721
No log	2.5859	256	0.5212	0.6659	0.5212	0.7219
No log	2.6061	258	0.7160	0.5233	0.7160	0.8462
No log	2.6263	260	0.7221	0.4580	0.7221	0.8497
No log	2.6465	262	0.5726	0.4901	0.5726	0.7567
No log	2.6667	264	0.4629	0.5599	0.4629	0.6803
No log	2.6869	266	0.4259	0.6264	0.4259	0.6526
No log	2.7071	268	0.4130	0.6564	0.4130	0.6426
No log	2.7273	270	0.4060	0.6488	0.4060	0.6372
No log	2.7475	272	0.4092	0.6694	0.4092	0.6397
No log	2.7677	274	0.4230	0.7175	0.4230	0.6504
No log	2.7879	276	0.5503	0.5953	0.5503	0.7418
No log	2.8081	278	0.6174	0.5455	0.6174	0.7857
No log	2.8283	280	0.5289	0.6188	0.5289	0.7273
No log	2.8485	282	0.4348	0.6377	0.4348	0.6594
No log	2.8687	284	0.4178	0.6303	0.4178	0.6464
No log	2.8889	286	0.4285	0.5560	0.4285	0.6546
No log	2.9091	288	0.4839	0.4733	0.4839	0.6956
No log	2.9293	290	0.5337	0.4651	0.5337	0.7305
No log	2.9495	292	0.5038	0.5155	0.5038	0.7098
No log	2.9697	294	0.4717	0.5880	0.4717	0.6868
No log	2.9899	296	0.4817	0.6284	0.4817	0.6940
No log	3.0101	298	0.4936	0.6336	0.4936	0.7025
No log	3.0303	300	0.4310	0.6946	0.4310	0.6565
No log	3.0505	302	0.4184	0.7028	0.4184	0.6468
No log	3.0707	304	0.4944	0.6255	0.4944	0.7032
No log	3.0909	306	0.5080	0.6313	0.5080	0.7128
No log	3.1111	308	0.4478	0.6972	0.4478	0.6692
No log	3.1313	310	0.4734	0.6913	0.4734	0.6881
No log	3.1515	312	0.5411	0.6360	0.5411	0.7356
No log	3.1717	314	0.5459	0.6367	0.5459	0.7388
No log	3.1919	316	0.5335	0.6552	0.5335	0.7304
No log	3.2121	318	0.4951	0.6289	0.4951	0.7036
No log	3.2323	320	0.5534	0.6154	0.5534	0.7439
No log	3.2525	322	0.5340	0.6382	0.5340	0.7308
No log	3.2727	324	0.4645	0.6822	0.4645	0.6816
No log	3.2929	326	0.5300	0.6255	0.5300	0.7280
No log	3.3131	328	0.5323	0.6188	0.5323	0.7296
No log	3.3333	330	0.4859	0.6475	0.4859	0.6971
No log	3.3535	332	0.8037	0.5090	0.8037	0.8965
No log	3.3737	334	1.0383	0.4066	1.0383	1.0190
No log	3.3939	336	0.9358	0.4225	0.9358	0.9674
No log	3.4141	338	0.6982	0.5351	0.6982	0.8356
No log	3.4343	340	0.4546	0.6613	0.4546	0.6742
No log	3.4545	342	0.4228	0.6513	0.4228	0.6503
No log	3.4747	344	0.4159	0.6534	0.4159	0.6449
No log	3.4949	346	0.4126	0.6701	0.4126	0.6423
No log	3.5152	348	0.4794	0.6609	0.4794	0.6924
No log	3.5354	350	0.6280	0.6011	0.6280	0.7925
No log	3.5556	352	0.6433	0.6017	0.6433	0.8021
No log	3.5758	354	0.6046	0.6257	0.6046	0.7776
No log	3.5960	356	0.5843	0.6432	0.5843	0.7644
No log	3.6162	358	0.6137	0.6347	0.6137	0.7834
No log	3.6364	360	0.5384	0.6956	0.5384	0.7338
No log	3.6566	362	0.4696	0.6935	0.4696	0.6852
No log	3.6768	364	0.4149	0.6971	0.4149	0.6441
No log	3.6970	366	0.3950	0.6830	0.3950	0.6285
No log	3.7172	368	0.4067	0.6970	0.4067	0.6377
No log	3.7374	370	0.4379	0.6542	0.4379	0.6617
No log	3.7576	372	0.4702	0.6351	0.4702	0.6857
No log	3.7778	374	0.5298	0.6325	0.5298	0.7279
No log	3.7980	376	0.4978	0.6568	0.4978	0.7055
No log	3.8182	378	0.4240	0.7229	0.4240	0.6512
No log	3.8384	380	0.4542	0.7255	0.4542	0.6739
No log	3.8586	382	0.4801	0.7224	0.4801	0.6929
No log	3.8788	384	0.6541	0.5992	0.6541	0.8088
No log	3.8990	386	0.8113	0.5203	0.8113	0.9007
No log	3.9192	388	0.8043	0.4722	0.8043	0.8969
No log	3.9394	390	0.6871	0.5415	0.6871	0.8289
No log	3.9596	392	0.5006	0.6487	0.5006	0.7075
No log	3.9798	394	0.4014	0.6952	0.4014	0.6336
No log	4.0	396	0.3954	0.7081	0.3954	0.6288
No log	4.0202	398	0.3888	0.7006	0.3888	0.6235
No log	4.0404	400	0.3961	0.6757	0.3961	0.6294
No log	4.0606	402	0.4855	0.6713	0.4855	0.6968
No log	4.0808	404	0.6802	0.5927	0.6802	0.8247
No log	4.1010	406	0.7531	0.5652	0.7531	0.8678
No log	4.1212	408	0.7370	0.5833	0.7370	0.8585
No log	4.1414	410	0.5869	0.6642	0.5869	0.7661
No log	4.1616	412	0.4251	0.7180	0.4251	0.6520
No log	4.1818	414	0.4382	0.6799	0.4382	0.6620
No log	4.2020	416	0.4375	0.6904	0.4375	0.6615
No log	4.2222	418	0.4337	0.7220	0.4337	0.6586
No log	4.2424	420	0.5478	0.6365	0.5478	0.7401
No log	4.2626	422	0.6164	0.5760	0.6164	0.7851
No log	4.2828	424	0.5083	0.6794	0.5083	0.7130
No log	4.3030	426	0.4537	0.7117	0.4537	0.6736
No log	4.3232	428	0.4351	0.7133	0.4351	0.6596
No log	4.3434	430	0.4543	0.7124	0.4543	0.6740
No log	4.3636	432	0.5776	0.6197	0.5776	0.7600
No log	4.3838	434	0.7524	0.5262	0.7524	0.8674
No log	4.4040	436	0.7590	0.5032	0.7590	0.8712
No log	4.4242	438	0.6817	0.5460	0.6817	0.8257
No log	4.4444	440	0.6062	0.5985	0.6062	0.7786
No log	4.4646	442	0.5581	0.6562	0.5581	0.7471
No log	4.4848	444	0.5730	0.6754	0.5730	0.7569
No log	4.5051	446	0.6333	0.6874	0.6333	0.7958
No log	4.5253	448	0.6988	0.6098	0.6988	0.8359
No log	4.5455	450	0.6742	0.6180	0.6742	0.8211
No log	4.5657	452	0.5538	0.6498	0.5538	0.7442
No log	4.5859	454	0.4457	0.6213	0.4457	0.6676
No log	4.6061	456	0.4182	0.6250	0.4182	0.6467
No log	4.6263	458	0.4380	0.6350	0.4380	0.6619
No log	4.6465	460	0.5240	0.6251	0.5240	0.7239
No log	4.6667	462	0.5389	0.6459	0.5389	0.7341
No log	4.6869	464	0.5117	0.6927	0.5117	0.7154
No log	4.7071	466	0.5187	0.7049	0.5187	0.7202
No log	4.7273	468	0.4985	0.7188	0.4985	0.7060
No log	4.7475	470	0.4804	0.6795	0.4804	0.6931
No log	4.7677	472	0.5161	0.6677	0.5161	0.7184
No log	4.7879	474	0.6234	0.5944	0.6234	0.7896
No log	4.8081	476	0.6180	0.6254	0.6180	0.7861
No log	4.8283	478	0.5394	0.6633	0.5394	0.7344
No log	4.8485	480	0.5032	0.7041	0.5032	0.7094
No log	4.8687	482	0.4854	0.7186	0.4854	0.6967
No log	4.8889	484	0.5197	0.6469	0.5197	0.7209
No log	4.9091	486	0.6987	0.5691	0.6987	0.8359
No log	4.9293	488	0.8566	0.4831	0.8566	0.9255
No log	4.9495	490	0.7736	0.5194	0.7736	0.8796
No log	4.9697	492	0.5160	0.5824	0.5160	0.7183
No log	4.9899	494	0.4634	0.6021	0.4634	0.6808
No log	5.0101	496	0.4314	0.6340	0.4314	0.6568
No log	5.0303	498	0.4743	0.6609	0.4743	0.6887
0.5311	5.0505	500	0.6548	0.6347	0.6548	0.8092
0.5311	5.0707	502	0.9260	0.5815	0.9260	0.9623
0.5311	5.0909	504	0.8772	0.5922	0.8772	0.9366
0.5311	5.1111	506	0.7710	0.6230	0.7710	0.8781
0.5311	5.1313	508	0.6076	0.6666	0.6076	0.7795
0.5311	5.1515	510	0.5119	0.6977	0.5119	0.7155
0.5311	5.1717	512	0.5983	0.6629	0.5983	0.7735
0.5311	5.1919	514	0.5607	0.6643	0.5607	0.7488
0.5311	5.2121	516	0.4336	0.6699	0.4336	0.6585
0.5311	5.2323	518	0.4463	0.6578	0.4463	0.6681
0.5311	5.2525	520	0.5635	0.5910	0.5635	0.7507
0.5311	5.2727	522	0.6719	0.5514	0.6719	0.8197
0.5311	5.2929	524	0.6379	0.6048	0.6379	0.7987
0.5311	5.3131	526	0.5615	0.6597	0.5615	0.7493
0.5311	5.3333	528	0.4546	0.7072	0.4546	0.6742
0.5311	5.3535	530	0.4233	0.6703	0.4233	0.6506
0.5311	5.3737	532	0.3957	0.6873	0.3957	0.6291
0.5311	5.3939	534	0.4237	0.6549	0.4237	0.6509
0.5311	5.4141	536	0.5246	0.6222	0.5246	0.7243
0.5311	5.4343	538	0.6562	0.5383	0.6562	0.8100
0.5311	5.4545	540	0.6706	0.5183	0.6706	0.8189
0.5311	5.4747	542	0.5935	0.5883	0.5935	0.7704
0.5311	5.4949	544	0.5122	0.6327	0.5122	0.7157

Framework versions

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