Arabic_CrossPrompt_FineTuningAraBERT_noAug_TestTask8_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: 0.7969
• Qwk: 0.5374
• Mse: 0.7969
• Rmse: 0.8927

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	4.2028	0.0080	4.2028	2.0501
No log	0.0392	4	3.4271	0.0371	3.4271	1.8513
No log	0.0588	6	2.0456	0.0905	2.0456	1.4303
No log	0.0784	8	0.8486	0.1595	0.8486	0.9212
No log	0.0980	10	0.8352	0.1567	0.8352	0.9139
No log	0.1176	12	0.8281	0.0984	0.8281	0.9100
No log	0.1373	14	0.7642	0.1434	0.7642	0.8742
No log	0.1569	16	0.6944	0.3722	0.6944	0.8333
No log	0.1765	18	0.6590	0.4091	0.6590	0.8118
No log	0.1961	20	0.6545	0.4167	0.6545	0.8090
No log	0.2157	22	0.6852	0.3834	0.6852	0.8277
No log	0.2353	24	0.7062	0.3668	0.7062	0.8404
No log	0.2549	26	0.6410	0.3873	0.6410	0.8006
No log	0.2745	28	0.5853	0.4292	0.5853	0.7650
No log	0.2941	30	0.6136	0.4244	0.6136	0.7833
No log	0.3137	32	0.7278	0.4165	0.7278	0.8531
No log	0.3333	34	0.8317	0.4086	0.8317	0.9120
No log	0.3529	36	0.7399	0.4341	0.7399	0.8602
No log	0.3725	38	0.7698	0.4474	0.7698	0.8774
No log	0.3922	40	0.6082	0.4597	0.6082	0.7799
No log	0.4118	42	0.5210	0.4820	0.5210	0.7218
No log	0.4314	44	0.5048	0.4942	0.5048	0.7105
No log	0.4510	46	0.5035	0.5103	0.5035	0.7096
No log	0.4706	48	0.4898	0.4948	0.4898	0.6999
No log	0.4902	50	0.4956	0.4669	0.4956	0.7040
No log	0.5098	52	0.5292	0.4410	0.5292	0.7275
No log	0.5294	54	0.5814	0.4288	0.5814	0.7625
No log	0.5490	56	0.6950	0.4713	0.6950	0.8337
No log	0.5686	58	0.6587	0.4969	0.6587	0.8116
No log	0.5882	60	0.6029	0.5220	0.6029	0.7765
No log	0.6078	62	0.6007	0.5169	0.6007	0.7750
No log	0.6275	64	0.6415	0.5577	0.6415	0.8009
No log	0.6471	66	0.5723	0.5874	0.5723	0.7565
No log	0.6667	68	0.5275	0.6132	0.5275	0.7263
No log	0.6863	70	0.5790	0.6336	0.5790	0.7609
No log	0.7059	72	0.5972	0.5911	0.5972	0.7728
No log	0.7255	74	0.6494	0.5874	0.6494	0.8059
No log	0.7451	76	0.8678	0.5119	0.8678	0.9316
No log	0.7647	78	0.9152	0.4787	0.9152	0.9567
No log	0.7843	80	0.6680	0.5298	0.6680	0.8173
No log	0.8039	82	0.4754	0.5369	0.4754	0.6895
No log	0.8235	84	0.5766	0.5217	0.5766	0.7594
No log	0.8431	86	0.6676	0.5125	0.6676	0.8171
No log	0.8627	88	0.5562	0.5228	0.5562	0.7458
No log	0.8824	90	0.5172	0.4973	0.5172	0.7191
No log	0.9020	92	0.5462	0.4516	0.5462	0.7391
No log	0.9216	94	0.5811	0.4616	0.5811	0.7623
No log	0.9412	96	0.6427	0.4692	0.6427	0.8017
No log	0.9608	98	0.5879	0.5257	0.5879	0.7667
No log	0.9804	100	0.6012	0.5745	0.6012	0.7754
No log	1.0	102	0.5486	0.6106	0.5486	0.7406
No log	1.0196	104	0.4630	0.6385	0.4630	0.6804
No log	1.0392	106	0.4667	0.6133	0.4667	0.6832
No log	1.0588	108	0.5729	0.4882	0.5729	0.7569
No log	1.0784	110	0.7200	0.4258	0.7200	0.8486
No log	1.0980	112	0.6863	0.4093	0.6863	0.8284
No log	1.1176	114	0.5664	0.4236	0.5664	0.7526
No log	1.1373	116	0.4650	0.5599	0.4650	0.6819
No log	1.1569	118	0.4927	0.5382	0.4927	0.7019
No log	1.1765	120	0.5366	0.6071	0.5366	0.7326
No log	1.1961	122	0.5779	0.6282	0.5779	0.7602
No log	1.2157	124	0.5514	0.6174	0.5514	0.7425
No log	1.2353	126	0.5628	0.5724	0.5628	0.7502
No log	1.2549	128	0.5000	0.6083	0.5000	0.7071
No log	1.2745	130	0.5029	0.5742	0.5029	0.7091
No log	1.2941	132	0.5439	0.5656	0.5439	0.7375
No log	1.3137	134	0.6366	0.5382	0.6366	0.7978
No log	1.3333	136	0.7002	0.5298	0.7002	0.8368
No log	1.3529	138	0.5557	0.6213	0.5557	0.7455
No log	1.3725	140	0.5366	0.5943	0.5366	0.7325
No log	1.3922	142	0.5883	0.5839	0.5883	0.7670
No log	1.4118	144	0.5009	0.6521	0.5009	0.7078
No log	1.4314	146	0.4676	0.6430	0.4676	0.6838
No log	1.4510	148	0.5600	0.6311	0.5600	0.7483
No log	1.4706	150	0.5597	0.6352	0.5597	0.7481
No log	1.4902	152	0.5690	0.5848	0.5690	0.7543
No log	1.5098	154	0.5653	0.5681	0.5653	0.7519
No log	1.5294	156	0.6915	0.4826	0.6915	0.8316
No log	1.5490	158	0.8726	0.4605	0.8726	0.9342
No log	1.5686	160	0.7721	0.4974	0.7721	0.8787
No log	1.5882	162	0.7522	0.5072	0.7522	0.8673
No log	1.6078	164	0.6101	0.5578	0.6101	0.7811
No log	1.6275	166	0.5041	0.5736	0.5041	0.7100
No log	1.6471	168	0.5381	0.6047	0.5381	0.7336
No log	1.6667	170	0.8870	0.4909	0.8870	0.9418
No log	1.6863	172	1.0403	0.4254	1.0403	1.0200
No log	1.7059	174	0.8430	0.4538	0.8430	0.9181
No log	1.7255	176	0.5552	0.5713	0.5552	0.7451
No log	1.7451	178	0.5027	0.5026	0.5027	0.7090
No log	1.7647	180	0.5807	0.4563	0.5807	0.7620
No log	1.7843	182	0.5704	0.4834	0.5704	0.7553
No log	1.8039	184	0.5813	0.4080	0.5813	0.7624
No log	1.8235	186	0.6386	0.2916	0.6386	0.7992
No log	1.8431	188	0.7190	0.2254	0.7190	0.8480
No log	1.8627	190	0.8469	0.1758	0.8469	0.9203
No log	1.8824	192	0.8621	0.3415	0.8621	0.9285
No log	1.9020	194	0.7047	0.4351	0.7047	0.8394
No log	1.9216	196	0.5603	0.5066	0.5603	0.7485
No log	1.9412	198	0.4576	0.6344	0.4576	0.6765
No log	1.9608	200	0.4936	0.6668	0.4936	0.7026
No log	1.9804	202	0.6451	0.5632	0.6451	0.8032
No log	2.0	204	0.6142	0.6079	0.6142	0.7837
No log	2.0196	206	0.5630	0.6411	0.5630	0.7504
No log	2.0392	208	0.4899	0.6657	0.4899	0.7000
No log	2.0588	210	0.4293	0.6958	0.4293	0.6552
No log	2.0784	212	0.4355	0.6798	0.4355	0.6599
No log	2.0980	214	0.5418	0.6221	0.5418	0.7360
No log	2.1176	216	0.7400	0.5469	0.7400	0.8603
No log	2.1373	218	0.7118	0.5523	0.7118	0.8437
No log	2.1569	220	0.6437	0.5793	0.6437	0.8023
No log	2.1765	222	0.6383	0.5848	0.6383	0.7989
No log	2.1961	224	0.5907	0.6118	0.5907	0.7686
No log	2.2157	226	0.5072	0.6337	0.5072	0.7122
No log	2.2353	228	0.4190	0.6720	0.4190	0.6473
No log	2.2549	230	0.4025	0.7015	0.4025	0.6344
No log	2.2745	232	0.4600	0.6760	0.4600	0.6782
No log	2.2941	234	0.7318	0.5258	0.7318	0.8555
No log	2.3137	236	0.8344	0.4906	0.8344	0.9134
No log	2.3333	238	0.6840	0.5477	0.6840	0.8270
No log	2.3529	240	0.5244	0.6467	0.5244	0.7241
No log	2.3725	242	0.4705	0.6825	0.4705	0.6860
No log	2.3922	244	0.4317	0.6942	0.4317	0.6570
No log	2.4118	246	0.4236	0.7175	0.4236	0.6509
No log	2.4314	248	0.4783	0.6984	0.4783	0.6916
No log	2.4510	250	0.6239	0.6278	0.6239	0.7899
No log	2.4706	252	0.6467	0.6043	0.6467	0.8042
No log	2.4902	254	0.5281	0.6168	0.5281	0.7267
No log	2.5098	256	0.4548	0.6052	0.4548	0.6744
No log	2.5294	258	0.4681	0.5230	0.4681	0.6842
No log	2.5490	260	0.5077	0.5701	0.5077	0.7125
No log	2.5686	262	0.5747	0.5600	0.5747	0.7581
No log	2.5882	264	0.6317	0.5469	0.6317	0.7948
No log	2.6078	266	0.7232	0.5441	0.7232	0.8504
No log	2.6275	268	0.6566	0.5713	0.6566	0.8103
No log	2.6471	270	0.4948	0.6160	0.4948	0.7034
No log	2.6667	272	0.4607	0.6522	0.4607	0.6787
No log	2.6863	274	0.4798	0.6513	0.4798	0.6927
No log	2.7059	276	0.5676	0.5983	0.5676	0.7534
No log	2.7255	278	0.7124	0.5380	0.7124	0.8440
No log	2.7451	280	0.7472	0.5073	0.7472	0.8644
No log	2.7647	282	0.6788	0.5330	0.6788	0.8239
No log	2.7843	284	0.5447	0.5361	0.5447	0.7381
No log	2.8039	286	0.4850	0.5377	0.4850	0.6964
No log	2.8235	288	0.4582	0.5715	0.4582	0.6769
No log	2.8431	290	0.4560	0.5750	0.4560	0.6753
No log	2.8627	292	0.5185	0.5108	0.5185	0.7200
No log	2.8824	294	0.6953	0.5266	0.6953	0.8338
No log	2.9020	296	0.7093	0.5248	0.7093	0.8422
No log	2.9216	298	0.6578	0.5382	0.6578	0.8110
No log	2.9412	300	0.5879	0.5025	0.5879	0.7667
No log	2.9608	302	0.4854	0.5429	0.4854	0.6967
No log	2.9804	304	0.4612	0.5523	0.4612	0.6791
No log	3.0	306	0.4575	0.5832	0.4575	0.6764
No log	3.0196	308	0.4770	0.6243	0.4770	0.6906
No log	3.0392	310	0.4921	0.6020	0.4921	0.7015
No log	3.0588	312	0.5417	0.6204	0.5417	0.7360
No log	3.0784	314	0.5700	0.6252	0.5700	0.7550
No log	3.0980	316	0.4814	0.6588	0.4814	0.6938
No log	3.1176	318	0.5436	0.6083	0.5436	0.7373
No log	3.1373	320	0.7317	0.5526	0.7317	0.8554
No log	3.1569	322	0.6342	0.6138	0.6342	0.7963
No log	3.1765	324	0.5151	0.6247	0.5151	0.7177
No log	3.1961	326	0.5262	0.6227	0.5262	0.7254
No log	3.2157	328	0.5643	0.5896	0.5643	0.7512
No log	3.2353	330	0.4952	0.6061	0.4952	0.7037
No log	3.2549	332	0.5142	0.5985	0.5142	0.7171
No log	3.2745	334	0.7440	0.5338	0.7440	0.8626
No log	3.2941	336	0.8428	0.5300	0.8428	0.9180
No log	3.3137	338	0.8321	0.5182	0.8321	0.9122
No log	3.3333	340	0.5716	0.5589	0.5716	0.7561
No log	3.3529	342	0.5056	0.6408	0.5056	0.7111
No log	3.3725	344	0.5729	0.6210	0.5729	0.7569
No log	3.3922	346	0.5973	0.6121	0.5973	0.7729
No log	3.4118	348	0.5498	0.6602	0.5498	0.7415
No log	3.4314	350	0.5443	0.6587	0.5443	0.7377
No log	3.4510	352	0.6391	0.6086	0.6391	0.7995
No log	3.4706	354	0.6005	0.5192	0.6005	0.7749
No log	3.4902	356	0.6895	0.3292	0.6895	0.8303
No log	3.5098	358	0.8094	0.1932	0.8094	0.8997
No log	3.5294	360	0.8024	0.2562	0.8024	0.8957
No log	3.5490	362	0.6969	0.3197	0.6969	0.8348
No log	3.5686	364	0.6155	0.5094	0.6155	0.7846
No log	3.5882	366	0.6393	0.4824	0.6393	0.7995
No log	3.6078	368	0.7794	0.3724	0.7794	0.8828
No log	3.6275	370	0.6976	0.4180	0.6976	0.8352
No log	3.6471	372	0.5479	0.4866	0.5479	0.7402
No log	3.6667	374	0.5129	0.5133	0.5129	0.7162
No log	3.6863	376	0.6475	0.5490	0.6475	0.8047
No log	3.7059	378	0.7942	0.4485	0.7942	0.8912
No log	3.7255	380	0.7677	0.4709	0.7677	0.8762
No log	3.7451	382	0.5582	0.6051	0.5582	0.7471
No log	3.7647	384	0.4967	0.6171	0.4967	0.7048
No log	3.7843	386	0.5318	0.6510	0.5318	0.7292
No log	3.8039	388	0.6150	0.5822	0.6150	0.7842
No log	3.8235	390	0.7397	0.5175	0.7397	0.8600
No log	3.8431	392	0.6503	0.5456	0.6503	0.8064
No log	3.8627	394	0.4484	0.6295	0.4484	0.6696
No log	3.8824	396	0.4386	0.6476	0.4386	0.6623
No log	3.9020	398	0.5039	0.6150	0.5039	0.7098
No log	3.9216	400	0.7088	0.5269	0.7088	0.8419
No log	3.9412	402	0.6560	0.5679	0.6560	0.8099
No log	3.9608	404	0.6068	0.6046	0.6068	0.7790
No log	3.9804	406	0.4797	0.7030	0.4797	0.6926
No log	4.0	408	0.4558	0.6764	0.4558	0.6751
No log	4.0196	410	0.4889	0.6181	0.4889	0.6992
No log	4.0392	412	0.5502	0.5906	0.5502	0.7417
No log	4.0588	414	0.5672	0.6302	0.5672	0.7531
No log	4.0784	416	0.6279	0.5855	0.6279	0.7924
No log	4.0980	418	0.5647	0.6194	0.5647	0.7515
No log	4.1176	420	0.4952	0.6164	0.4952	0.7037
No log	4.1373	422	0.5627	0.6221	0.5627	0.7502
No log	4.1569	424	0.6554	0.5627	0.6554	0.8096
No log	4.1765	426	0.6072	0.5577	0.6072	0.7792
No log	4.1961	428	0.5032	0.5421	0.5032	0.7094
No log	4.2157	430	0.4495	0.6093	0.4495	0.6705
No log	4.2353	432	0.4830	0.5749	0.4830	0.6950
No log	4.2549	434	0.7438	0.5140	0.7438	0.8624
No log	4.2745	436	0.8947	0.4814	0.8947	0.9459
No log	4.2941	438	0.6155	0.5693	0.6155	0.7845
No log	4.3137	440	0.4795	0.6393	0.4795	0.6924
No log	4.3333	442	0.4364	0.6829	0.4364	0.6606
No log	4.3529	444	0.4950	0.6844	0.4950	0.7035
No log	4.3725	446	0.6704	0.6125	0.6704	0.8188
No log	4.3922	448	0.9262	0.5017	0.9262	0.9624
No log	4.4118	450	0.9333	0.5040	0.9333	0.9661
No log	4.4314	452	0.6555	0.6209	0.6555	0.8096
No log	4.4510	454	0.4543	0.6796	0.4543	0.6740
No log	4.4706	456	0.4260	0.7153	0.4260	0.6527
No log	4.4902	458	0.4473	0.6799	0.4473	0.6688
No log	4.5098	460	0.5031	0.6539	0.5031	0.7093
No log	4.5294	462	0.6924	0.5582	0.6924	0.8321
No log	4.5490	464	0.7793	0.5567	0.7793	0.8828
No log	4.5686	466	0.8041	0.5496	0.8041	0.8967
No log	4.5882	468	0.6789	0.5724	0.6789	0.8240
No log	4.6078	470	0.5906	0.5878	0.5906	0.7685
No log	4.6275	472	0.6496	0.5730	0.6496	0.8060
No log	4.6471	474	0.6565	0.5726	0.6565	0.8103
No log	4.6667	476	0.5515	0.6183	0.5515	0.7426
No log	4.6863	478	0.4906	0.6131	0.4906	0.7004
No log	4.7059	480	0.4961	0.6401	0.4961	0.7044
No log	4.7255	482	0.5161	0.6097	0.5161	0.7184
No log	4.7451	484	0.4811	0.6356	0.4811	0.6936
No log	4.7647	486	0.4396	0.6549	0.4396	0.6630
No log	4.7843	488	0.5068	0.6134	0.5068	0.7119
No log	4.8039	490	0.6040	0.5434	0.6040	0.7772
No log	4.8235	492	0.6759	0.5205	0.6759	0.8221
No log	4.8431	494	0.6934	0.5232	0.6934	0.8327
No log	4.8627	496	0.5441	0.6315	0.5441	0.7376
No log	4.8824	498	0.4488	0.6579	0.4488	0.6699
0.5646	4.9020	500	0.4816	0.6774	0.4816	0.6940
0.5646	4.9216	502	0.4861	0.6668	0.4861	0.6972
0.5646	4.9412	504	0.5821	0.6069	0.5821	0.7630
0.5646	4.9608	506	0.8333	0.5237	0.8333	0.9129
0.5646	4.9804	508	1.0599	0.4574	1.0599	1.0295
0.5646	5.0	510	0.7969	0.5374	0.7969	0.8927

Framework versions

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