ArabicNewSplits5_FineTuningAraBERT_run3_AugV5_k6_task3_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: 0.6395
• Qwk: 0.2919
• Mse: 0.6395
• Rmse: 0.7997

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	0.0541	2	3.2269	-0.0126	3.2269	1.7964
No log	0.1081	4	1.4189	-0.0070	1.4189	1.1912
No log	0.1622	6	1.0754	0.0294	1.0754	1.0370
No log	0.2162	8	0.7957	0.1481	0.7957	0.8920
No log	0.2703	10	0.6021	0.1667	0.6021	0.7760
No log	0.3243	12	0.7028	0.1038	0.7028	0.8383
No log	0.3784	14	1.2073	0.0794	1.2073	1.0988
No log	0.4324	16	1.3260	0.0345	1.3260	1.1515
No log	0.4865	18	1.2496	0.0698	1.2496	1.1179
No log	0.5405	20	0.8438	0.1667	0.8438	0.9186
No log	0.5946	22	0.6700	0.0222	0.6700	0.8185
No log	0.6486	24	0.6814	-0.0732	0.6814	0.8255
No log	0.7027	26	0.6928	-0.0794	0.6928	0.8324
No log	0.7568	28	0.7771	0.1264	0.7771	0.8815
No log	0.8108	30	1.2236	-0.0233	1.2236	1.1062
No log	0.8649	32	1.1989	-0.0233	1.1989	1.0949
No log	0.9189	34	0.8811	0.0476	0.8811	0.9387
No log	0.9730	36	0.6581	0.0638	0.6581	0.8112
No log	1.0270	38	0.6011	-0.0233	0.6011	0.7753
No log	1.0811	40	0.5792	-0.0233	0.5792	0.7611
No log	1.1351	42	0.5863	-0.0496	0.5863	0.7657
No log	1.1892	44	0.6470	0.3333	0.6470	0.8043
No log	1.2432	46	1.1772	0.0745	1.1772	1.0850
No log	1.2973	48	1.4794	0.0698	1.4794	1.2163
No log	1.3514	50	1.3350	0.0698	1.3350	1.1554
No log	1.4054	52	1.0373	0.1276	1.0373	1.0185
No log	1.4595	54	0.6631	0.2593	0.6631	0.8143
No log	1.5135	56	0.5911	0.1795	0.5911	0.7688
No log	1.5676	58	0.5950	0.1795	0.5950	0.7714
No log	1.6216	60	0.5854	0.2000	0.5854	0.7651
No log	1.6757	62	0.7391	0.2000	0.7391	0.8597
No log	1.7297	64	0.8486	0.25	0.8486	0.9212
No log	1.7838	66	0.5668	0.1605	0.5668	0.7529
No log	1.8378	68	0.5631	0.0365	0.5631	0.7504
No log	1.8919	70	0.7722	0.1892	0.7722	0.8788
No log	1.9459	72	0.6638	0.2298	0.6638	0.8148
No log	2.0	74	0.5477	0.1373	0.5477	0.7401
No log	2.0541	76	0.5843	0.1807	0.5843	0.7644
No log	2.1081	78	0.6240	0.1392	0.6240	0.7900
No log	2.1622	80	0.6752	0.1617	0.6752	0.8217
No log	2.2162	82	0.6646	0.2471	0.6646	0.8152
No log	2.2703	84	0.8715	0.0741	0.8715	0.9335
No log	2.3243	86	0.8966	0.0370	0.8966	0.9469
No log	2.3784	88	0.7588	0.2527	0.7588	0.8711
No log	2.4324	90	0.9064	-0.0563	0.9064	0.9521
No log	2.4865	92	0.9038	0.0207	0.9038	0.9507
No log	2.5405	94	0.7315	0.2889	0.7315	0.8553
No log	2.5946	96	0.6948	0.2990	0.6948	0.8336
No log	2.6486	98	0.8291	0.1130	0.8291	0.9105
No log	2.7027	100	1.0728	-0.0725	1.0728	1.0358
No log	2.7568	102	0.9240	0.0901	0.9240	0.9612
No log	2.8108	104	0.5905	0.3258	0.5905	0.7684
No log	2.8649	106	0.8894	0.2140	0.8894	0.9431
No log	2.9189	108	0.7644	0.1698	0.7644	0.8743
No log	2.9730	110	0.5192	0.3032	0.5192	0.7206
No log	3.0270	112	0.6389	0.2704	0.6389	0.7993
No log	3.0811	114	0.6062	0.3171	0.6062	0.7786
No log	3.1351	116	0.5035	0.3032	0.5035	0.7096
No log	3.1892	118	0.5114	0.3136	0.5114	0.7152
No log	3.2432	120	0.4998	0.2308	0.4998	0.7070
No log	3.2973	122	0.5796	0.2889	0.5796	0.7613
No log	3.3514	124	0.7311	0.1923	0.7311	0.8551
No log	3.4054	126	0.6783	0.25	0.6783	0.8236
No log	3.4595	128	0.7771	0.2881	0.7771	0.8815
No log	3.5135	130	1.0179	0.0769	1.0179	1.0089
No log	3.5676	132	0.9597	0.1571	0.9597	0.9796
No log	3.6216	134	0.7571	0.3147	0.7571	0.8701
No log	3.6757	136	0.5996	0.3116	0.5996	0.7744
No log	3.7297	138	0.6047	0.3128	0.6047	0.7776
No log	3.7838	140	0.7711	0.2727	0.7711	0.8781
No log	3.8378	142	1.1922	0.0671	1.1922	1.0919
No log	3.8919	144	1.2117	0.0671	1.2117	1.1008
No log	3.9459	146	0.8742	0.1545	0.8742	0.9350
No log	4.0	148	0.6189	0.3951	0.6189	0.7867
No log	4.0541	150	0.6256	0.3077	0.6256	0.7910
No log	4.1081	152	0.6425	0.2821	0.6425	0.8016
No log	4.1622	154	0.5308	0.4043	0.5308	0.7286
No log	4.2162	156	0.7293	0.3427	0.7293	0.8540
No log	4.2703	158	0.8762	0.1938	0.8762	0.9360
No log	4.3243	160	0.7118	0.3052	0.7118	0.8437
No log	4.3784	162	0.5172	0.3797	0.5172	0.7192
No log	4.4324	164	0.5752	0.2563	0.5752	0.7584
No log	4.4865	166	0.5443	0.3061	0.5443	0.7378
No log	4.5405	168	0.5843	0.3831	0.5843	0.7644
No log	4.5946	170	0.8723	0.1939	0.8723	0.9340
No log	4.6486	172	0.9434	0.1367	0.9434	0.9713
No log	4.7027	174	0.7655	0.2941	0.7655	0.8749
No log	4.7568	176	0.6517	0.4185	0.6517	0.8073
No log	4.8108	178	0.6483	0.4286	0.6483	0.8052
No log	4.8649	180	0.7549	0.2961	0.7549	0.8689
No log	4.9189	182	0.9941	0.1661	0.9941	0.9970
No log	4.9730	184	0.9745	0.1661	0.9745	0.9872
No log	5.0270	186	0.8194	0.2593	0.8194	0.9052
No log	5.0811	188	0.8583	0.2258	0.8583	0.9264
No log	5.1351	190	0.7100	0.3667	0.7100	0.8426
No log	5.1892	192	0.5851	0.3171	0.5851	0.7649
No log	5.2432	194	0.5715	0.3706	0.5715	0.7560
No log	5.2973	196	0.6358	0.2780	0.6358	0.7973
No log	5.3514	198	0.8060	0.2941	0.8060	0.8978
No log	5.4054	200	0.7835	0.2941	0.7835	0.8852
No log	5.4595	202	0.5795	0.3730	0.5795	0.7613
No log	5.5135	204	0.5170	0.3043	0.5170	0.7191
No log	5.5676	206	0.5609	0.3402	0.5609	0.7490
No log	5.6216	208	0.4929	0.3407	0.4929	0.7021
No log	5.6757	210	0.4976	0.3374	0.4976	0.7054
No log	5.7297	212	0.5952	0.3089	0.5952	0.7715
No log	5.7838	214	0.6327	0.3398	0.6327	0.7954
No log	5.8378	216	0.7725	0.3251	0.7725	0.8789
No log	5.8919	218	0.7885	0.3171	0.7885	0.8880
No log	5.9459	220	0.6397	0.4035	0.6397	0.7998
No log	6.0	222	0.6122	0.4118	0.6122	0.7824
No log	6.0541	224	0.6927	0.4035	0.6927	0.8323
No log	6.1081	226	0.7516	0.3871	0.7516	0.8670
No log	6.1622	228	0.8181	0.3092	0.8181	0.9045
No log	6.2162	230	0.8961	0.2481	0.8961	0.9466
No log	6.2703	232	0.7154	0.3188	0.7154	0.8458
No log	6.3243	234	0.5984	0.3398	0.5984	0.7736
No log	6.3784	236	0.5318	0.3469	0.5318	0.7292
No log	6.4324	238	0.5247	0.3684	0.5247	0.7244
No log	6.4865	240	0.5848	0.3369	0.5848	0.7648
No log	6.5405	242	0.6829	0.2579	0.6829	0.8264
No log	6.5946	244	0.7676	0.2881	0.7676	0.8761
No log	6.6486	246	0.6892	0.2593	0.6892	0.8302
No log	6.7027	248	0.6498	0.2621	0.6498	0.8061
No log	6.7568	250	0.6425	0.2919	0.6425	0.8016
No log	6.8108	252	0.5838	0.3831	0.5838	0.7641
No log	6.8649	254	0.5701	0.3862	0.5701	0.7551
No log	6.9189	256	0.5857	0.3103	0.5857	0.7653
No log	6.9730	258	0.5875	0.4043	0.5875	0.7665
No log	7.0270	260	0.6236	0.1832	0.6236	0.7897
No log	7.0811	262	0.6506	0.1837	0.6506	0.8066
No log	7.1351	264	0.6782	0.2222	0.6782	0.8235
No log	7.1892	266	0.6100	0.24	0.6100	0.7810
No log	7.2432	268	0.5979	0.3398	0.5979	0.7732
No log	7.2973	270	0.6049	0.3103	0.6049	0.7777
No log	7.3514	272	0.6244	0.3427	0.6244	0.7902
No log	7.4054	274	0.6346	0.3427	0.6346	0.7966
No log	7.4595	276	0.6912	0.2233	0.6912	0.8314
No log	7.5135	278	0.6837	0.2793	0.6837	0.8269
No log	7.5676	280	0.6605	0.3761	0.6605	0.8127
No log	7.6216	282	0.7088	0.2593	0.7088	0.8419
No log	7.6757	284	0.7607	0.2881	0.7607	0.8722
No log	7.7297	286	0.7058	0.2607	0.7058	0.8401
No log	7.7838	288	0.6450	0.3267	0.6450	0.8031
No log	7.8378	290	0.6034	0.3299	0.6034	0.7768
No log	7.8919	292	0.5965	0.3299	0.5965	0.7723
No log	7.9459	294	0.5842	0.3797	0.5842	0.7643
No log	8.0	296	0.6086	0.2965	0.6086	0.7801
No log	8.0541	298	0.6939	0.2227	0.6939	0.8330
No log	8.1081	300	0.7284	0.2566	0.7284	0.8534
No log	8.1622	302	0.6874	0.2227	0.6874	0.8291
No log	8.2162	304	0.6496	0.2941	0.6496	0.8060
No log	8.2703	306	0.6561	0.2941	0.6561	0.8100
No log	8.3243	308	0.6518	0.2941	0.6518	0.8073
No log	8.3784	310	0.6551	0.2941	0.6551	0.8094
No log	8.4324	312	0.6415	0.2941	0.6415	0.8009
No log	8.4865	314	0.6173	0.2965	0.6173	0.7857
No log	8.5405	316	0.6164	0.2965	0.6164	0.7851
No log	8.5946	318	0.6197	0.2965	0.6197	0.7872
No log	8.6486	320	0.6526	0.2941	0.6526	0.8079
No log	8.7027	322	0.7139	0.2227	0.7139	0.8449
No log	8.7568	324	0.7770	0.2554	0.7770	0.8815
No log	8.8108	326	0.7829	0.2554	0.7829	0.8848
No log	8.8649	328	0.7378	0.2566	0.7378	0.8590
No log	8.9189	330	0.6788	0.2227	0.6788	0.8239
No log	8.9730	332	0.6353	0.2941	0.6353	0.7970
No log	9.0270	334	0.6100	0.2941	0.6100	0.7811
No log	9.0811	336	0.5837	0.3846	0.5837	0.7640
No log	9.1351	338	0.5693	0.3829	0.5693	0.7545
No log	9.1892	340	0.5599	0.3829	0.5599	0.7483
No log	9.2432	342	0.5622	0.3829	0.5622	0.7498
No log	9.2973	344	0.5760	0.3898	0.5760	0.7589
No log	9.3514	346	0.6050	0.3237	0.6050	0.7778
No log	9.4054	348	0.6417	0.2897	0.6417	0.8010
No log	9.4595	350	0.6602	0.2593	0.6602	0.8125
No log	9.5135	352	0.6615	0.2593	0.6615	0.8133
No log	9.5676	354	0.6564	0.3242	0.6564	0.8102
No log	9.6216	356	0.6482	0.2897	0.6482	0.8051
No log	9.6757	358	0.6415	0.2897	0.6415	0.8009
No log	9.7297	360	0.6352	0.2919	0.6352	0.7970
No log	9.7838	362	0.6310	0.2919	0.6310	0.7944
No log	9.8378	364	0.6328	0.2919	0.6328	0.7955
No log	9.8919	366	0.6354	0.2919	0.6354	0.7971
No log	9.9459	368	0.6380	0.2919	0.6380	0.7988
No log	10.0	370	0.6395	0.2919	0.6395	0.7997

Framework versions

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