ArabicNewSplits6_WithDuplicationsForScore5_FineTuningAraBERT_run3_AugV5_k6_task1_organization

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: 1.0043
• Qwk: 0.5737
• Mse: 1.0043
• Rmse: 1.0022

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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	0.0556	2	5.2469	-0.0111	5.2469	2.2906
No log	0.1111	4	3.2751	0.0818	3.2751	1.8097
No log	0.1667	6	2.2291	-0.0153	2.2291	1.4930
No log	0.2222	8	1.5187	0.1576	1.5187	1.2323
No log	0.2778	10	1.2004	0.2565	1.2004	1.0956
No log	0.3333	12	1.1149	0.2552	1.1149	1.0559
No log	0.3889	14	1.0988	0.3050	1.0988	1.0482
No log	0.4444	16	1.0968	0.3310	1.0968	1.0473
No log	0.5	18	0.9906	0.2665	0.9906	0.9953
No log	0.5556	20	1.0613	0.3858	1.0613	1.0302
No log	0.6111	22	1.2054	0.2482	1.2054	1.0979
No log	0.6667	24	1.3662	0.1668	1.3662	1.1688
No log	0.7222	26	1.6590	0.1628	1.6590	1.2880
No log	0.7778	28	1.6178	0.2039	1.6178	1.2719
No log	0.8333	30	1.2013	0.3057	1.2013	1.0960
No log	0.8889	32	0.9300	0.4869	0.9300	0.9644
No log	0.9444	34	0.9305	0.4883	0.9305	0.9646
No log	1.0	36	0.8981	0.4987	0.8981	0.9477
No log	1.0556	38	0.9113	0.5735	0.9113	0.9546
No log	1.1111	40	0.9019	0.5676	0.9019	0.9497
No log	1.1667	42	0.8636	0.5574	0.8636	0.9293
No log	1.2222	44	0.8134	0.5410	0.8134	0.9019
No log	1.2778	46	0.8083	0.5458	0.8083	0.8991
No log	1.3333	48	0.7926	0.6393	0.7926	0.8903
No log	1.3889	50	0.8683	0.5798	0.8683	0.9318
No log	1.4444	52	0.8400	0.6097	0.8400	0.9165
No log	1.5	54	0.8212	0.6184	0.8212	0.9062
No log	1.5556	56	0.7999	0.6265	0.7999	0.8944
No log	1.6111	58	0.7857	0.5942	0.7857	0.8864
No log	1.6667	60	0.7837	0.5903	0.7837	0.8852
No log	1.7222	62	0.7773	0.6192	0.7773	0.8816
No log	1.7778	64	0.7523	0.6314	0.7523	0.8673
No log	1.8333	66	0.7616	0.6348	0.7616	0.8727
No log	1.8889	68	0.7639	0.6649	0.7639	0.8740
No log	1.9444	70	0.7323	0.6311	0.7323	0.8558
No log	2.0	72	0.7811	0.6431	0.7811	0.8838
No log	2.0556	74	0.8533	0.6401	0.8533	0.9237
No log	2.1111	76	0.8097	0.6561	0.8097	0.8998
No log	2.1667	78	0.8021	0.6418	0.8021	0.8956
No log	2.2222	80	0.8554	0.6551	0.8554	0.9249
No log	2.2778	82	0.9214	0.6069	0.9214	0.9599
No log	2.3333	84	0.9266	0.6100	0.9266	0.9626
No log	2.3889	86	0.8842	0.5963	0.8842	0.9403
No log	2.4444	88	0.7912	0.6342	0.7912	0.8895
No log	2.5	90	0.7644	0.6433	0.7644	0.8743
No log	2.5556	92	0.7595	0.6692	0.7595	0.8715
No log	2.6111	94	0.8079	0.6400	0.8079	0.8989
No log	2.6667	96	0.7911	0.6269	0.7911	0.8895
No log	2.7222	98	0.7595	0.6779	0.7595	0.8715
No log	2.7778	100	0.7216	0.6815	0.7216	0.8494
No log	2.8333	102	0.7200	0.6570	0.7200	0.8485
No log	2.8889	104	0.7542	0.6686	0.7542	0.8684
No log	2.9444	106	0.8376	0.6200	0.8376	0.9152
No log	3.0	108	0.8923	0.5742	0.8923	0.9446
No log	3.0556	110	0.9077	0.5642	0.9077	0.9527
No log	3.1111	112	0.8862	0.5823	0.8862	0.9414
No log	3.1667	114	0.8448	0.5871	0.8448	0.9192
No log	3.2222	116	0.8024	0.6154	0.8024	0.8958
No log	3.2778	118	0.8022	0.6062	0.8022	0.8957
No log	3.3333	120	0.8041	0.6159	0.8041	0.8967
No log	3.3889	122	0.8069	0.6420	0.8069	0.8983
No log	3.4444	124	0.8712	0.6102	0.8712	0.9334
No log	3.5	126	0.9100	0.6027	0.9100	0.9539
No log	3.5556	128	0.9323	0.6158	0.9323	0.9655
No log	3.6111	130	0.9729	0.5799	0.9729	0.9863
No log	3.6667	132	0.9956	0.5877	0.9956	0.9978
No log	3.7222	134	0.9196	0.6478	0.9196	0.9589
No log	3.7778	136	0.8526	0.6414	0.8526	0.9233
No log	3.8333	138	0.8700	0.6261	0.8700	0.9327
No log	3.8889	140	0.9301	0.6183	0.9301	0.9644
No log	3.9444	142	1.0484	0.5803	1.0484	1.0239
No log	4.0	144	1.1091	0.5741	1.1091	1.0532
No log	4.0556	146	1.1110	0.5659	1.1110	1.0541
No log	4.1111	148	0.9923	0.6155	0.9923	0.9961
No log	4.1667	150	0.8453	0.6297	0.8453	0.9194
No log	4.2222	152	0.7781	0.6229	0.7781	0.8821
No log	4.2778	154	0.7775	0.6135	0.7775	0.8817
No log	4.3333	156	0.8172	0.6073	0.8172	0.9040
No log	4.3889	158	0.8941	0.5990	0.8941	0.9455
No log	4.4444	160	0.9801	0.6226	0.9801	0.9900
No log	4.5	162	1.0383	0.6121	1.0383	1.0190
No log	4.5556	164	0.9879	0.6045	0.9879	0.9939
No log	4.6111	166	0.9332	0.6031	0.9332	0.9660
No log	4.6667	168	0.9445	0.6193	0.9445	0.9719
No log	4.7222	170	0.9444	0.6196	0.9444	0.9718
No log	4.7778	172	0.9084	0.6231	0.9084	0.9531
No log	4.8333	174	0.9431	0.6223	0.9431	0.9711
No log	4.8889	176	1.0156	0.5974	1.0156	1.0078
No log	4.9444	178	1.0278	0.5863	1.0278	1.0138
No log	5.0	180	0.9856	0.6179	0.9856	0.9928
No log	5.0556	182	0.9552	0.6171	0.9552	0.9774
No log	5.1111	184	0.9237	0.6175	0.9237	0.9611
No log	5.1667	186	0.8798	0.6397	0.8798	0.9380
No log	5.2222	188	0.8816	0.6368	0.8816	0.9389
No log	5.2778	190	0.9744	0.6141	0.9744	0.9871
No log	5.3333	192	1.1355	0.5899	1.1355	1.0656
No log	5.3889	194	1.1864	0.5829	1.1864	1.0892
No log	5.4444	196	1.1050	0.5883	1.1050	1.0512
No log	5.5	198	0.9617	0.6084	0.9617	0.9807
No log	5.5556	200	0.8779	0.5689	0.8779	0.9369
No log	5.6111	202	0.8490	0.5888	0.8490	0.9214
No log	5.6667	204	0.8715	0.6091	0.8715	0.9336
No log	5.7222	206	0.8456	0.6266	0.8456	0.9196
No log	5.7778	208	0.8197	0.6309	0.8197	0.9054
No log	5.8333	210	0.8443	0.6472	0.8443	0.9189
No log	5.8889	212	0.9337	0.5952	0.9337	0.9663
No log	5.9444	214	1.0544	0.5808	1.0544	1.0268
No log	6.0	216	1.1363	0.5744	1.1363	1.0660
No log	6.0556	218	1.1875	0.5405	1.1875	1.0897
No log	6.1111	220	1.1396	0.5661	1.1396	1.0675
No log	6.1667	222	1.0506	0.5820	1.0506	1.0250
No log	6.2222	224	0.9929	0.5718	0.9929	0.9964
No log	6.2778	226	0.9012	0.5872	0.9012	0.9493
No log	6.3333	228	0.8361	0.5865	0.8361	0.9144
No log	6.3889	230	0.8236	0.6002	0.8236	0.9075
No log	6.4444	232	0.8635	0.6005	0.8635	0.9292
No log	6.5	234	0.9298	0.5891	0.9298	0.9643
No log	6.5556	236	0.9828	0.5762	0.9828	0.9913
No log	6.6111	238	0.9979	0.5873	0.9979	0.9989
No log	6.6667	240	0.9551	0.5884	0.9551	0.9773
No log	6.7222	242	0.9131	0.5950	0.9131	0.9556
No log	6.7778	244	0.8860	0.6069	0.8860	0.9413
No log	6.8333	246	0.8772	0.6081	0.8772	0.9366
No log	6.8889	248	0.8534	0.6444	0.8534	0.9238
No log	6.9444	250	0.8256	0.6150	0.8256	0.9086
No log	7.0	252	0.8100	0.6219	0.8100	0.9000
No log	7.0556	254	0.8225	0.6219	0.8225	0.9069
No log	7.1111	256	0.8724	0.6146	0.8724	0.9340
No log	7.1667	258	0.9208	0.5671	0.9208	0.9596
No log	7.2222	260	0.9941	0.5620	0.9941	0.9970
No log	7.2778	262	1.0648	0.5572	1.0648	1.0319
No log	7.3333	264	1.1314	0.5324	1.1314	1.0637
No log	7.3889	266	1.1461	0.5329	1.1461	1.0706
No log	7.4444	268	1.1316	0.5386	1.1316	1.0638
No log	7.5	270	1.1303	0.5168	1.1303	1.0632
No log	7.5556	272	1.0894	0.5474	1.0894	1.0438
No log	7.6111	274	1.0301	0.5529	1.0301	1.0149
No log	7.6667	276	0.9999	0.5620	0.9999	0.9999
No log	7.7222	278	0.9828	0.5723	0.9828	0.9914
No log	7.7778	280	0.9487	0.5755	0.9487	0.9740
No log	7.8333	282	0.9431	0.5851	0.9431	0.9712
No log	7.8889	284	0.9402	0.5862	0.9402	0.9696
No log	7.9444	286	0.9524	0.5839	0.9524	0.9759
No log	8.0	288	0.9425	0.6255	0.9425	0.9708
No log	8.0556	290	0.9177	0.6255	0.9177	0.9580
No log	8.1111	292	0.9184	0.6255	0.9184	0.9583
No log	8.1667	294	0.9070	0.6247	0.9070	0.9524
No log	8.2222	296	0.8750	0.6256	0.8750	0.9354
No log	8.2778	298	0.8442	0.6236	0.8442	0.9188
No log	8.3333	300	0.8357	0.6355	0.8357	0.9142
No log	8.3889	302	0.8367	0.6340	0.8367	0.9147
No log	8.4444	304	0.8532	0.6370	0.8532	0.9237
No log	8.5	306	0.8848	0.6233	0.8848	0.9406
No log	8.5556	308	0.9282	0.6207	0.9282	0.9635
No log	8.6111	310	0.9798	0.5757	0.9798	0.9899
No log	8.6667	312	1.0149	0.5757	1.0149	1.0074
No log	8.7222	314	1.0286	0.5759	1.0286	1.0142
No log	8.7778	316	1.0399	0.5738	1.0399	1.0198
No log	8.8333	318	1.0238	0.5803	1.0238	1.0118
No log	8.8889	320	0.9937	0.5791	0.9937	0.9969
No log	8.9444	322	0.9652	0.5721	0.9652	0.9824
No log	9.0	324	0.9555	0.5721	0.9555	0.9775
No log	9.0556	326	0.9555	0.5721	0.9555	0.9775
No log	9.1111	328	0.9538	0.5825	0.9538	0.9766
No log	9.1667	330	0.9529	0.5825	0.9529	0.9762
No log	9.2222	332	0.9576	0.5814	0.9576	0.9786
No log	9.2778	334	0.9650	0.5675	0.9650	0.9823
No log	9.3333	336	0.9702	0.5675	0.9702	0.9850
No log	9.3889	338	0.9834	0.5746	0.9834	0.9917
No log	9.4444	340	0.9920	0.5737	0.9920	0.9960
No log	9.5	342	0.9997	0.5737	0.9997	0.9998
No log	9.5556	344	1.0025	0.5737	1.0025	1.0013
No log	9.6111	346	1.0051	0.5737	1.0051	1.0025
No log	9.6667	348	1.0062	0.5737	1.0062	1.0031
No log	9.7222	350	1.0081	0.5737	1.0081	1.0041
No log	9.7778	352	1.0077	0.5737	1.0077	1.0038
No log	9.8333	354	1.0051	0.5737	1.0051	1.0026
No log	9.8889	356	1.0047	0.5737	1.0047	1.0024
No log	9.9444	358	1.0047	0.5737	1.0047	1.0023
No log	10.0	360	1.0043	0.5737	1.0043	1.0022

Framework versions

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