Arabic_CrossPrompt_FineTuningAraBERT_noAug_TestTask5_mechanics

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: 0.6629
• Qwk: 0.5108
• Mse: 0.6629
• Rmse: 0.8142

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	0.0198	2	3.8617	-0.0092	3.8617	1.9651
No log	0.0396	4	2.6708	0.0310	2.6708	1.6342
No log	0.0594	6	1.3010	0.0197	1.3010	1.1406
No log	0.0792	8	0.8395	0.0637	0.8395	0.9162
No log	0.0990	10	0.7702	0.0530	0.7702	0.8776
No log	0.1188	12	0.8885	0.0550	0.8885	0.9426
No log	0.1386	14	0.9194	0.0758	0.9194	0.9588
No log	0.1584	16	0.6914	0.2202	0.6914	0.8315
No log	0.1782	18	0.7209	0.3713	0.7209	0.8491
No log	0.1980	20	0.5993	0.3471	0.5993	0.7741
No log	0.2178	22	0.6421	0.1849	0.6421	0.8013
No log	0.2376	24	0.6373	0.2013	0.6373	0.7983
No log	0.2574	26	0.6311	0.2013	0.6311	0.7944
No log	0.2772	28	0.6292	0.2013	0.6292	0.7932
No log	0.2970	30	0.5974	0.2420	0.5974	0.7729
No log	0.3168	32	0.5493	0.3263	0.5493	0.7411
No log	0.3366	34	0.5119	0.4198	0.5119	0.7155
No log	0.3564	36	0.5513	0.4613	0.5513	0.7425
No log	0.3762	38	0.6337	0.4087	0.6337	0.7961
No log	0.3960	40	0.7654	0.2274	0.7654	0.8748
No log	0.4158	42	0.8136	0.1957	0.8136	0.9020
No log	0.4356	44	0.7318	0.2772	0.7318	0.8554
No log	0.4554	46	0.5844	0.3982	0.5844	0.7645
No log	0.4752	48	0.5534	0.4157	0.5534	0.7439
No log	0.4950	50	0.5680	0.3954	0.5680	0.7536
No log	0.5149	52	0.5084	0.3945	0.5084	0.7130
No log	0.5347	54	0.5034	0.3945	0.5034	0.7095
No log	0.5545	56	0.5291	0.3760	0.5291	0.7274
No log	0.5743	58	0.6171	0.4075	0.6171	0.7856
No log	0.5941	60	0.6795	0.4419	0.6795	0.8243
No log	0.6139	62	0.6949	0.4893	0.6949	0.8336
No log	0.6337	64	0.6698	0.4837	0.6698	0.8184
No log	0.6535	66	0.7925	0.4519	0.7925	0.8902
No log	0.6733	68	0.8471	0.4167	0.8471	0.9204
No log	0.6931	70	0.7485	0.4517	0.7485	0.8652
No log	0.7129	72	0.6046	0.5315	0.6046	0.7776
No log	0.7327	74	0.6103	0.4870	0.6103	0.7812
No log	0.7525	76	0.5509	0.5020	0.5509	0.7422
No log	0.7723	78	0.5180	0.4157	0.5180	0.7197
No log	0.7921	80	0.5215	0.3787	0.5215	0.7221
No log	0.8119	82	0.5545	0.3091	0.5545	0.7446
No log	0.8317	84	0.6126	0.2440	0.6126	0.7827
No log	0.8515	86	0.6265	0.2547	0.6265	0.7915
No log	0.8713	88	0.5431	0.3292	0.5431	0.7369
No log	0.8911	90	0.5208	0.3907	0.5208	0.7217
No log	0.9109	92	0.5392	0.3956	0.5392	0.7343
No log	0.9307	94	0.5103	0.4439	0.5103	0.7143
No log	0.9505	96	0.4857	0.5204	0.4857	0.6969
No log	0.9703	98	0.5201	0.5178	0.5201	0.7212
No log	0.9901	100	0.4870	0.5092	0.4870	0.6978
No log	1.0099	102	0.5222	0.5078	0.5222	0.7227
No log	1.0297	104	0.6350	0.5072	0.6350	0.7969
No log	1.0495	106	0.6131	0.5071	0.6131	0.7830
No log	1.0693	108	0.5264	0.5312	0.5264	0.7255
No log	1.0891	110	0.4585	0.5091	0.4585	0.6772
No log	1.1089	112	0.4678	0.4881	0.4678	0.6840
No log	1.1287	114	0.4898	0.5158	0.4898	0.6999
No log	1.1485	116	0.4911	0.5095	0.4911	0.7008
No log	1.1683	118	0.5066	0.5273	0.5066	0.7118
No log	1.1881	120	0.5295	0.5168	0.5295	0.7277
No log	1.2079	122	0.5362	0.5305	0.5362	0.7322
No log	1.2277	124	0.6386	0.5365	0.6386	0.7991
No log	1.2475	126	0.6736	0.5295	0.6736	0.8207
No log	1.2673	128	0.5472	0.6013	0.5472	0.7397
No log	1.2871	130	0.5629	0.5561	0.5629	0.7503
No log	1.3069	132	0.5445	0.5659	0.5445	0.7379
No log	1.3267	134	0.5199	0.5647	0.5199	0.7210
No log	1.3465	136	0.6233	0.5449	0.6233	0.7895
No log	1.3663	138	0.6798	0.4330	0.6798	0.8245
No log	1.3861	140	0.6013	0.2891	0.6013	0.7755
No log	1.4059	142	0.5443	0.4013	0.5443	0.7378
No log	1.4257	144	0.5542	0.4227	0.5542	0.7444
No log	1.4455	146	0.4947	0.5085	0.4947	0.7034
No log	1.4653	148	0.4765	0.5164	0.4765	0.6903
No log	1.4851	150	0.4475	0.5027	0.4475	0.6689
No log	1.5050	152	0.4383	0.4449	0.4383	0.6620
No log	1.5248	154	0.4563	0.4289	0.4563	0.6755
No log	1.5446	156	0.5375	0.4053	0.5375	0.7331
No log	1.5644	158	0.5854	0.4317	0.5854	0.7651
No log	1.5842	160	0.5606	0.4641	0.5606	0.7487
No log	1.6040	162	0.5749	0.5137	0.5749	0.7582
No log	1.6238	164	0.5382	0.5508	0.5382	0.7336
No log	1.6436	166	0.4505	0.5488	0.4505	0.6712
No log	1.6634	168	0.4394	0.5298	0.4394	0.6629
No log	1.6832	170	0.4619	0.4930	0.4619	0.6796
No log	1.7030	172	0.5726	0.5386	0.5726	0.7567
No log	1.7228	174	0.5491	0.5315	0.5491	0.7410
No log	1.7426	176	0.5584	0.5295	0.5584	0.7473
No log	1.7624	178	0.5884	0.5711	0.5884	0.7671
No log	1.7822	180	0.7149	0.4925	0.7149	0.8455
No log	1.8020	182	0.7508	0.4577	0.7508	0.8665
No log	1.8218	184	0.6324	0.5331	0.6324	0.7953
No log	1.8416	186	0.5526	0.5869	0.5526	0.7434
No log	1.8614	188	0.5603	0.5093	0.5603	0.7486
No log	1.8812	190	0.5213	0.4945	0.5213	0.7220
No log	1.9010	192	0.5167	0.5064	0.5167	0.7188
No log	1.9208	194	0.5780	0.5186	0.5780	0.7603
No log	1.9406	196	0.5679	0.5268	0.5679	0.7536
No log	1.9604	198	0.5583	0.5197	0.5583	0.7472
No log	1.9802	200	0.5533	0.5292	0.5533	0.7439
No log	2.0	202	0.6812	0.4850	0.6812	0.8253
No log	2.0198	204	0.7210	0.4653	0.7210	0.8491
No log	2.0396	206	0.7390	0.4538	0.7390	0.8596
No log	2.0594	208	0.6205	0.5221	0.6205	0.7877
No log	2.0792	210	0.4917	0.6338	0.4917	0.7012
No log	2.0990	212	0.4554	0.6139	0.4554	0.6748
No log	2.1188	214	0.4523	0.6164	0.4523	0.6726
No log	2.1386	216	0.4669	0.6317	0.4669	0.6833
No log	2.1584	218	0.4899	0.5918	0.4899	0.6999
No log	2.1782	220	0.6284	0.4574	0.6284	0.7927
No log	2.1980	222	0.7109	0.3982	0.7109	0.8432
No log	2.2178	224	0.6544	0.3818	0.6544	0.8090
No log	2.2376	226	0.6232	0.4320	0.6232	0.7894
No log	2.2574	228	0.6151	0.4827	0.6151	0.7843
No log	2.2772	230	0.5834	0.5344	0.5834	0.7638
No log	2.2970	232	0.6033	0.5288	0.6033	0.7767
No log	2.3168	234	0.5716	0.5592	0.5716	0.7560
No log	2.3366	236	0.6245	0.5239	0.6245	0.7903
No log	2.3564	238	0.6614	0.5288	0.6614	0.8132
No log	2.3762	240	0.6682	0.5196	0.6682	0.8174
No log	2.3960	242	0.5870	0.5356	0.5870	0.7661
No log	2.4158	244	0.5378	0.5238	0.5378	0.7334
No log	2.4356	246	0.4849	0.5010	0.4849	0.6964
No log	2.4554	248	0.4867	0.4928	0.4867	0.6977
No log	2.4752	250	0.4744	0.5068	0.4744	0.6887
No log	2.4950	252	0.5030	0.5218	0.5030	0.7092
No log	2.5149	254	0.5863	0.4944	0.5863	0.7657
No log	2.5347	256	0.6555	0.4922	0.6555	0.8097
No log	2.5545	258	0.5930	0.5346	0.5930	0.7701
No log	2.5743	260	0.5346	0.5328	0.5346	0.7312
No log	2.5941	262	0.5249	0.5312	0.5249	0.7245
No log	2.6139	264	0.4947	0.5462	0.4947	0.7034
No log	2.6337	266	0.4764	0.5475	0.4764	0.6902
No log	2.6535	268	0.5198	0.5187	0.5198	0.7209
No log	2.6733	270	0.6949	0.4601	0.6949	0.8336
No log	2.6931	272	0.7838	0.4613	0.7838	0.8853
No log	2.7129	274	0.6651	0.4864	0.6651	0.8155
No log	2.7327	276	0.4772	0.4990	0.4772	0.6908
No log	2.7525	278	0.4507	0.5610	0.4507	0.6713
No log	2.7723	280	0.4439	0.5678	0.4439	0.6663
No log	2.7921	282	0.4663	0.5845	0.4663	0.6828
No log	2.8119	284	0.6081	0.5154	0.6081	0.7798
No log	2.8317	286	0.7362	0.4758	0.7362	0.8580
No log	2.8515	288	0.7187	0.4909	0.7187	0.8478
No log	2.8713	290	0.5792	0.5543	0.5792	0.7611
No log	2.8911	292	0.5046	0.6572	0.5046	0.7104
No log	2.9109	294	0.4692	0.6576	0.4692	0.6850
No log	2.9307	296	0.4506	0.6332	0.4506	0.6713
No log	2.9505	298	0.4376	0.6252	0.4376	0.6615
No log	2.9703	300	0.4806	0.6024	0.4806	0.6933
No log	2.9901	302	0.5084	0.5836	0.5084	0.7130
No log	3.0099	304	0.5619	0.5252	0.5619	0.7496
No log	3.0297	306	0.5251	0.5462	0.5251	0.7246
No log	3.0495	308	0.4726	0.5630	0.4726	0.6875
No log	3.0693	310	0.4438	0.6108	0.4438	0.6662
No log	3.0891	312	0.4343	0.6153	0.4343	0.6590
No log	3.1089	314	0.4430	0.6146	0.4430	0.6656
No log	3.1287	316	0.4914	0.5736	0.4914	0.7010
No log	3.1485	318	0.5198	0.5603	0.5198	0.7210
No log	3.1683	320	0.6252	0.5169	0.6252	0.7907
No log	3.1881	322	0.6753	0.5014	0.6753	0.8218
No log	3.2079	324	0.7212	0.4805	0.7212	0.8492
No log	3.2277	326	0.6528	0.5467	0.6528	0.8080
No log	3.2475	328	0.5781	0.5547	0.5781	0.7603
No log	3.2673	330	0.5587	0.5802	0.5587	0.7474
No log	3.2871	332	0.5387	0.5770	0.5387	0.7340
No log	3.3069	334	0.5959	0.5635	0.5959	0.7720
No log	3.3267	336	0.8060	0.4574	0.8060	0.8978
No log	3.3465	338	0.7892	0.4572	0.7892	0.8884
No log	3.3663	340	0.6894	0.5051	0.6894	0.8303
No log	3.3861	342	0.5406	0.5686	0.5406	0.7352
No log	3.4059	344	0.4761	0.5927	0.4761	0.6900
No log	3.4257	346	0.4562	0.6188	0.4562	0.6754
No log	3.4455	348	0.4470	0.5898	0.4470	0.6686
No log	3.4653	350	0.5308	0.5313	0.5308	0.7286
No log	3.4851	352	0.7782	0.4415	0.7782	0.8822
No log	3.5050	354	0.9864	0.3469	0.9864	0.9932
No log	3.5248	356	1.0520	0.2693	1.0520	1.0257
No log	3.5446	358	0.9337	0.3670	0.9337	0.9663
No log	3.5644	360	0.6812	0.4511	0.6812	0.8253
No log	3.5842	362	0.5265	0.5886	0.5265	0.7256
No log	3.6040	364	0.5040	0.6165	0.5040	0.7099
No log	3.6238	366	0.5414	0.5822	0.5414	0.7358
No log	3.6436	368	0.6413	0.5178	0.6413	0.8008
No log	3.6634	370	0.8952	0.4432	0.8952	0.9461
No log	3.6832	372	1.0418	0.3874	1.0418	1.0207
No log	3.7030	374	0.9404	0.4207	0.9404	0.9697
No log	3.7228	376	0.6394	0.4944	0.6394	0.7996
No log	3.7426	378	0.4587	0.5469	0.4587	0.6772
No log	3.7624	380	0.4407	0.5331	0.4407	0.6638
No log	3.7822	382	0.4429	0.5382	0.4429	0.6655
No log	3.8020	384	0.6048	0.5451	0.6048	0.7777
No log	3.8218	386	0.9436	0.3963	0.9436	0.9714
No log	3.8416	388	1.1027	0.3728	1.1027	1.0501
No log	3.8614	390	0.9847	0.4324	0.9847	0.9923
No log	3.8812	392	0.6700	0.5520	0.6700	0.8185
No log	3.9010	394	0.4657	0.6125	0.4657	0.6824
No log	3.9208	396	0.4385	0.6316	0.4385	0.6622
No log	3.9406	398	0.4337	0.6190	0.4337	0.6586
No log	3.9604	400	0.4529	0.5932	0.4529	0.6730
No log	3.9802	402	0.5188	0.5440	0.5188	0.7203
No log	4.0	404	0.6488	0.5137	0.6488	0.8055
No log	4.0198	406	0.7404	0.4607	0.7404	0.8604
No log	4.0396	408	0.6531	0.5255	0.6531	0.8081
No log	4.0594	410	0.5545	0.5550	0.5545	0.7446
No log	4.0792	412	0.5601	0.6037	0.5601	0.7484
No log	4.0990	414	0.5499	0.6011	0.5499	0.7416
No log	4.1188	416	0.5342	0.5616	0.5342	0.7309
No log	4.1386	418	0.6243	0.5239	0.6243	0.7901
No log	4.1584	420	0.6982	0.4979	0.6982	0.8356
No log	4.1782	422	0.6762	0.5100	0.6762	0.8223
No log	4.1980	424	0.5551	0.5553	0.5551	0.7451
No log	4.2178	426	0.5672	0.5611	0.5672	0.7531
No log	4.2376	428	0.7633	0.4828	0.7633	0.8737
No log	4.2574	430	1.0393	0.4088	1.0393	1.0195
No log	4.2772	432	0.9470	0.4325	0.9470	0.9731
No log	4.2970	434	0.5947	0.5360	0.5947	0.7711
No log	4.3168	436	0.4211	0.5804	0.4211	0.6489
No log	4.3366	438	0.4197	0.5973	0.4197	0.6479
No log	4.3564	440	0.4091	0.5869	0.4091	0.6396
No log	4.3762	442	0.5696	0.5361	0.5696	0.7547
No log	4.3960	444	0.9019	0.4502	0.9019	0.9497
No log	4.4158	446	0.9234	0.4532	0.9234	0.9609
No log	4.4356	448	0.6939	0.5228	0.6939	0.8330
No log	4.4554	450	0.4853	0.6063	0.4853	0.6966
No log	4.4752	452	0.4508	0.6143	0.4508	0.6714
No log	4.4950	454	0.4342	0.5896	0.4342	0.6589
No log	4.5149	456	0.4693	0.5929	0.4693	0.6850
No log	4.5347	458	0.6005	0.5412	0.6005	0.7749
No log	4.5545	460	0.7180	0.4593	0.7180	0.8473
No log	4.5743	462	0.7230	0.4808	0.7230	0.8503
No log	4.5941	464	0.5962	0.5433	0.5962	0.7721
No log	4.6139	466	0.5187	0.6068	0.5187	0.7202
No log	4.6337	468	0.4900	0.6108	0.4900	0.7000
No log	4.6535	470	0.5072	0.5926	0.5072	0.7121
No log	4.6733	472	0.5888	0.5638	0.5888	0.7673
No log	4.6931	474	0.6263	0.5508	0.6263	0.7914
No log	4.7129	476	0.6395	0.5364	0.6395	0.7997
No log	4.7327	478	0.5587	0.5769	0.5587	0.7474
No log	4.7525	480	0.5039	0.5827	0.5039	0.7099
No log	4.7723	482	0.6146	0.5361	0.6146	0.7840
No log	4.7921	484	0.6599	0.5050	0.6599	0.8123
No log	4.8119	486	0.8304	0.4618	0.8304	0.9113
No log	4.8317	488	0.7874	0.4649	0.7874	0.8874
No log	4.8515	490	0.5999	0.5501	0.5999	0.7745
No log	4.8713	492	0.4606	0.5991	0.4606	0.6787
No log	4.8911	494	0.4523	0.6034	0.4523	0.6725
No log	4.9109	496	0.4620	0.5777	0.4620	0.6797
No log	4.9307	498	0.5313	0.5340	0.5313	0.7289
0.5166	4.9505	500	0.5833	0.5529	0.5833	0.7637
0.5166	4.9703	502	0.5502	0.5689	0.5502	0.7417
0.5166	4.9901	504	0.5811	0.5457	0.5811	0.7623
0.5166	5.0099	506	0.5416	0.5633	0.5416	0.7359
0.5166	5.0297	508	0.5390	0.5519	0.5390	0.7342
0.5166	5.0495	510	0.5595	0.5481	0.5595	0.7480
0.5166	5.0693	512	0.5283	0.5343	0.5283	0.7268
0.5166	5.0891	514	0.5274	0.5595	0.5274	0.7262
0.5166	5.1089	516	0.6608	0.5478	0.6608	0.8129
0.5166	5.1287	518	0.9321	0.5007	0.9321	0.9655
0.5166	5.1485	520	0.8450	0.5444	0.8450	0.9193
0.5166	5.1683	522	0.5809	0.6105	0.5809	0.7622
0.5166	5.1881	524	0.5297	0.5619	0.5297	0.7278
0.5166	5.2079	526	0.5529	0.6079	0.5529	0.7436
0.5166	5.2277	528	0.6843	0.5644	0.6843	0.8272
0.5166	5.2475	530	0.9172	0.4790	0.9172	0.9577
0.5166	5.2673	532	1.0803	0.3700	1.0803	1.0394
0.5166	5.2871	534	1.0016	0.4118	1.0016	1.0008
0.5166	5.3069	536	0.6384	0.5211	0.6384	0.7990
0.5166	5.3267	538	0.4502	0.6001	0.4502	0.6709
0.5166	5.3465	540	0.4228	0.6043	0.4228	0.6502
0.5166	5.3663	542	0.4696	0.5842	0.4696	0.6853
0.5166	5.3861	544	0.5439	0.5594	0.5439	0.7375
0.5166	5.4059	546	0.6653	0.5349	0.6653	0.8156
0.5166	5.4257	548	0.8481	0.4397	0.8481	0.9209
0.5166	5.4455	550	0.8194	0.4712	0.8194	0.9052
0.5166	5.4653	552	0.6488	0.5648	0.6488	0.8055
0.5166	5.4851	554	0.4847	0.6244	0.4847	0.6962
0.5166	5.5050	556	0.4544	0.6603	0.4544	0.6741
0.5166	5.5248	558	0.4540	0.6499	0.4540	0.6738
0.5166	5.5446	560	0.6044	0.5957	0.6044	0.7774
0.5166	5.5644	562	0.7090	0.5350	0.7090	0.8420
0.5166	5.5842	564	0.6564	0.5491	0.6564	0.8102
0.5166	5.6040	566	0.6215	0.5723	0.6215	0.7884
0.5166	5.6238	568	0.6553	0.5522	0.6553	0.8095
0.5166	5.6436	570	0.5303	0.5743	0.5303	0.7282
0.5166	5.6634	572	0.4597	0.5852	0.4597	0.6780
0.5166	5.6832	574	0.4640	0.5723	0.4640	0.6812
0.5166	5.7030	576	0.5667	0.5165	0.5667	0.7528
0.5166	5.7228	578	0.7228	0.4818	0.7228	0.8502
0.5166	5.7426	580	0.9582	0.4241	0.9582	0.9789
0.5166	5.7624	582	0.8591	0.4680	0.8591	0.9269
0.5166	5.7822	584	0.6629	0.5108	0.6629	0.8142

Framework versions

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