ArabicNewSplits5_FineTuningAraBERT_run1_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: 0.6700
• Qwk: 0.3149
• Mse: 0.6700
• Rmse: 0.8185

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	3.0983	-0.0075	3.0983	1.7602
No log	0.1081	4	1.5332	-0.0070	1.5332	1.2382
No log	0.1622	6	1.9073	0.0545	1.9073	1.3811
No log	0.2162	8	2.5486	0.0572	2.5486	1.5964
No log	0.2703	10	1.5519	0.0255	1.5519	1.2457
No log	0.3243	12	0.9658	0.0	0.9658	0.9827
No log	0.3784	14	1.0100	0.0345	1.0100	1.0050
No log	0.4324	16	1.0155	0.0345	1.0155	1.0077
No log	0.4865	18	1.2652	0.0	1.2652	1.1248
No log	0.5405	20	1.2200	0.0	1.2200	1.1045
No log	0.5946	22	1.1359	0.0	1.1359	1.0658
No log	0.6486	24	1.1096	0.0	1.1096	1.0534
No log	0.7027	26	1.0539	0.0078	1.0539	1.0266
No log	0.7568	28	0.9474	-0.0256	0.9474	0.9734
No log	0.8108	30	0.9063	0.0741	0.9063	0.9520
No log	0.8649	32	1.0032	0.0894	1.0032	1.0016
No log	0.9189	34	1.2771	0.0118	1.2771	1.1301
No log	0.9730	36	1.2900	0.0388	1.2900	1.1358
No log	1.0270	38	0.9370	0.0118	0.9370	0.9680
No log	1.0811	40	0.8755	0.0968	0.8755	0.9357
No log	1.1351	42	1.1217	0.0149	1.1217	1.0591
No log	1.1892	44	0.7730	0.0409	0.7730	0.8792
No log	1.2432	46	0.5893	0.0303	0.5893	0.7677
No log	1.2973	48	0.6218	0.1565	0.6218	0.7885
No log	1.3514	50	1.0686	0.1317	1.0686	1.0337
No log	1.4054	52	1.7807	0.0567	1.7807	1.3344
No log	1.4595	54	1.3227	0.0286	1.3227	1.1501
No log	1.5135	56	0.7168	0.1443	0.7168	0.8466
No log	1.5676	58	0.5723	0.0569	0.5723	0.7565
No log	1.6216	60	0.6466	0.0	0.6466	0.8041
No log	1.6757	62	0.5648	0.0569	0.5648	0.7516
No log	1.7297	64	0.5960	0.2340	0.5960	0.7720
No log	1.7838	66	1.0475	0.0431	1.0475	1.0235
No log	1.8378	68	1.4574	0.0	1.4574	1.2072
No log	1.8919	70	1.4087	0.0	1.4087	1.1869
No log	1.9459	72	1.1342	0.0	1.1342	1.0650
No log	2.0	74	0.9586	-0.0268	0.9586	0.9791
No log	2.0541	76	0.8473	0.0118	0.8473	0.9205
No log	2.1081	78	0.6454	0.2857	0.6454	0.8034
No log	2.1622	80	0.5792	0.2653	0.5792	0.7611
No log	2.2162	82	0.6100	0.2201	0.6100	0.7810
No log	2.2703	84	0.7464	0.3333	0.7464	0.8639
No log	2.3243	86	0.7642	0.3035	0.7642	0.8742
No log	2.3784	88	0.5679	0.2941	0.5679	0.7536
No log	2.4324	90	0.6304	0.2911	0.6304	0.7940
No log	2.4865	92	0.5896	0.2795	0.5896	0.7678
No log	2.5405	94	0.6887	0.2511	0.6887	0.8299
No log	2.5946	96	1.1600	0.1781	1.1600	1.0770
No log	2.6486	98	0.9283	0.1877	0.9283	0.9635
No log	2.7027	100	0.5666	0.2626	0.5666	0.7528
No log	2.7568	102	0.8303	0.1264	0.8303	0.9112
No log	2.8108	104	0.7438	0.2857	0.7438	0.8624
No log	2.8649	106	0.5432	0.2418	0.5432	0.7370
No log	2.9189	108	0.7617	0.2146	0.7617	0.8728
No log	2.9730	110	0.9673	0.1613	0.9673	0.9835
No log	3.0270	112	1.2305	0.0701	1.2305	1.1093
No log	3.0811	114	1.1671	0.0701	1.1671	1.0803
No log	3.1351	116	0.9133	0.1673	0.9133	0.9557
No log	3.1892	118	0.7032	0.2410	0.7032	0.8385
No log	3.2432	120	0.5779	0.2201	0.5779	0.7602
No log	3.2973	122	0.5584	0.1565	0.5584	0.7473
No log	3.3514	124	0.5969	0.3369	0.5969	0.7726
No log	3.4054	126	0.6794	0.3333	0.6794	0.8242
No log	3.4595	128	0.7814	0.2302	0.7814	0.8840
No log	3.5135	130	0.8342	0.2226	0.8342	0.9133
No log	3.5676	132	0.7774	0.2797	0.7774	0.8817
No log	3.6216	134	0.7759	0.2906	0.7759	0.8809
No log	3.6757	136	0.8771	0.2353	0.8771	0.9365
No log	3.7297	138	0.9556	0.1661	0.9556	0.9776
No log	3.7838	140	0.9304	0.1533	0.9304	0.9646
No log	3.8378	142	0.8346	0.1746	0.8346	0.9136
No log	3.8919	144	0.7707	0.2667	0.7707	0.8779
No log	3.9459	146	0.8481	0.2000	0.8481	0.9209
No log	4.0	148	0.8698	0.1515	0.8698	0.9326
No log	4.0541	150	0.6870	0.2340	0.6870	0.8288
No log	4.1081	152	0.8495	0.1786	0.8495	0.9217
No log	4.1622	154	1.0720	0.1254	1.0720	1.0354
No log	4.2162	156	0.9005	0.1475	0.9005	0.9489
No log	4.2703	158	0.6330	0.3224	0.6330	0.7956
No log	4.3243	160	0.6524	0.2746	0.6524	0.8077
No log	4.3784	162	0.7428	0.3394	0.7428	0.8619
No log	4.4324	164	0.7557	0.3363	0.7557	0.8693
No log	4.4865	166	0.6680	0.3607	0.6680	0.8173
No log	4.5405	168	0.6828	0.3739	0.6828	0.8263
No log	4.5946	170	0.8159	0.2885	0.8159	0.9033
No log	4.6486	172	0.9423	0.2664	0.9423	0.9707
No log	4.7027	174	1.0172	0.1586	1.0172	1.0086
No log	4.7568	176	0.8895	0.2329	0.8895	0.9431
No log	4.8108	178	0.6392	0.3116	0.6392	0.7995
No log	4.8649	180	0.7437	0.2469	0.7437	0.8624
No log	4.9189	182	1.0048	0.2126	1.0048	1.0024
No log	4.9730	184	0.8255	0.2275	0.8255	0.9085
No log	5.0270	186	0.5979	0.2809	0.5979	0.7733
No log	5.0811	188	0.7921	0.1795	0.7921	0.8900
No log	5.1351	190	0.8807	0.1241	0.8807	0.9385
No log	5.1892	192	0.7474	0.1786	0.7474	0.8645
No log	5.2432	194	0.6573	0.4404	0.6573	0.8107
No log	5.2973	196	0.5787	0.4220	0.5787	0.7607
No log	5.3514	198	0.5444	0.2663	0.5444	0.7378
No log	5.4054	200	0.5434	0.2558	0.5434	0.7372
No log	5.4595	202	0.5450	0.2941	0.5450	0.7382
No log	5.5135	204	0.5873	0.2593	0.5873	0.7664
No log	5.5676	206	0.5524	0.3684	0.5524	0.7432
No log	5.6216	208	0.5766	0.3295	0.5766	0.7593
No log	5.6757	210	0.6716	0.2621	0.6716	0.8195
No log	5.7297	212	0.6442	0.2965	0.6442	0.8026
No log	5.7838	214	0.5420	0.3488	0.5420	0.7362
No log	5.8378	216	0.5873	0.3508	0.5873	0.7664
No log	5.8919	218	0.6178	0.36	0.6178	0.7860
No log	5.9459	220	0.5648	0.3862	0.5648	0.7515
No log	6.0	222	0.6620	0.2711	0.6620	0.8136
No log	6.0541	224	0.9167	0.2177	0.9167	0.9574
No log	6.1081	226	0.9487	0.2174	0.9487	0.9740
No log	6.1622	228	0.7662	0.2941	0.7662	0.8753
No log	6.2162	230	0.6173	0.3846	0.6173	0.7857
No log	6.2703	232	0.6266	0.4234	0.6266	0.7916
No log	6.3243	234	0.6187	0.4118	0.6187	0.7866
No log	6.3784	236	0.7155	0.2881	0.7155	0.8458
No log	6.4324	238	0.9831	0.2180	0.9831	0.9915
No log	6.4865	240	1.0144	0.2174	1.0144	1.0072
No log	6.5405	242	0.8298	0.2188	0.8298	0.9109
No log	6.5946	244	0.6168	0.4229	0.6168	0.7853
No log	6.6486	246	0.5632	0.3224	0.5632	0.7505
No log	6.7027	248	0.5641	0.375	0.5641	0.7510
No log	6.7568	250	0.5556	0.3103	0.5556	0.7454
No log	6.8108	252	0.5777	0.2749	0.5777	0.7600
No log	6.8649	254	0.6198	0.3575	0.6198	0.7873
No log	6.9189	256	0.6661	0.3706	0.6661	0.8161
No log	6.9730	258	0.6309	0.3191	0.6309	0.7943
No log	7.0270	260	0.6058	0.2381	0.6058	0.7783
No log	7.0811	262	0.6222	0.3224	0.6222	0.7888
No log	7.1351	264	0.6765	0.3077	0.6765	0.8225
No log	7.1892	266	0.7512	0.2681	0.7512	0.8667
No log	7.2432	268	0.7753	0.2667	0.7753	0.8805
No log	7.2973	270	0.7195	0.2554	0.7195	0.8483
No log	7.3514	272	0.6614	0.3398	0.6614	0.8133
No log	7.4054	274	0.6916	0.2381	0.6916	0.8316
No log	7.4595	276	0.7217	0.3043	0.7217	0.8495
No log	7.5135	278	0.6818	0.2000	0.6818	0.8257
No log	7.5676	280	0.6605	0.3641	0.6605	0.8127
No log	7.6216	282	0.7425	0.2542	0.7425	0.8617
No log	7.6757	284	0.8473	0.2126	0.8473	0.9205
No log	7.7297	286	0.8383	0.2062	0.8383	0.9156
No log	7.7838	288	0.7413	0.2269	0.7413	0.8610
No log	7.8378	290	0.6739	0.3035	0.6739	0.8209
No log	7.8919	292	0.6355	0.2994	0.6355	0.7972
No log	7.9459	294	0.6354	0.2832	0.6354	0.7971
No log	8.0	296	0.6394	0.2179	0.6394	0.7996
No log	8.0541	298	0.6262	0.2941	0.6262	0.7913
No log	8.1081	300	0.6269	0.2542	0.6269	0.7918
No log	8.1622	302	0.6637	0.3878	0.6637	0.8147
No log	8.2162	304	0.6952	0.2381	0.6952	0.8338
No log	8.2703	306	0.7071	0.2453	0.7071	0.8409
No log	8.3243	308	0.6757	0.2842	0.6757	0.8220
No log	8.3784	310	0.6356	0.2281	0.6356	0.7972
No log	8.4324	312	0.6207	0.2663	0.6207	0.7878
No log	8.4865	314	0.6240	0.3149	0.6240	0.7899
No log	8.5405	316	0.6226	0.2663	0.6226	0.7891
No log	8.5946	318	0.6239	0.2663	0.6239	0.7899
No log	8.6486	320	0.6256	0.2289	0.6256	0.7909
No log	8.7027	322	0.6307	0.2289	0.6307	0.7942
No log	8.7568	324	0.6396	0.2289	0.6396	0.7997
No log	8.8108	326	0.6467	0.2727	0.6467	0.8042
No log	8.8649	328	0.6631	0.3548	0.6631	0.8143
No log	8.9189	330	0.6760	0.3548	0.6760	0.8222
No log	8.9730	332	0.7104	0.2000	0.7104	0.8429
No log	9.0270	334	0.7598	0.2070	0.7598	0.8717
No log	9.0811	336	0.7692	0.2070	0.7692	0.8771
No log	9.1351	338	0.7476	0.2281	0.7476	0.8646
No log	9.1892	340	0.7116	0.4010	0.7116	0.8436
No log	9.2432	342	0.6873	0.3641	0.6873	0.8290
No log	9.2973	344	0.6775	0.2865	0.6775	0.8231
No log	9.3514	346	0.6757	0.2889	0.6757	0.8220
No log	9.4054	348	0.6726	0.2889	0.6726	0.8201
No log	9.4595	350	0.6696	0.2787	0.6696	0.8183
No log	9.5135	352	0.6656	0.2889	0.6656	0.8159
No log	9.5676	354	0.6628	0.2889	0.6628	0.8141
No log	9.6216	356	0.6606	0.2865	0.6606	0.8128
No log	9.6757	358	0.6600	0.2865	0.6600	0.8124
No log	9.7297	360	0.6596	0.2865	0.6596	0.8121
No log	9.7838	362	0.6616	0.2941	0.6616	0.8134
No log	9.8378	364	0.6632	0.2727	0.6632	0.8144
No log	9.8919	366	0.6662	0.2727	0.6662	0.8162
No log	9.9459	368	0.6688	0.3149	0.6688	0.8178
No log	10.0	370	0.6700	0.3149	0.6700	0.8185

Framework versions

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