ArabicNewSplits6_FineTuningAraBERT_run2_AugV5_k8_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: 0.5306
• Qwk: 0.3023
• Mse: 0.5306
• Rmse: 0.7284

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	0.0513	2	3.3364	-0.0066	3.3364	1.8266
No log	0.1026	4	1.7436	-0.0070	1.7436	1.3204
No log	0.1538	6	1.3009	0.0294	1.3009	1.1406
No log	0.2051	8	0.6288	0.1795	0.6288	0.7930
No log	0.2564	10	0.5897	0.0476	0.5897	0.7679
No log	0.3077	12	1.2716	0.0929	1.2716	1.1277
No log	0.3590	14	0.9003	0.0698	0.9003	0.9489
No log	0.4103	16	0.5536	0.0	0.5536	0.7440
No log	0.4615	18	0.5851	0.0	0.5851	0.7649
No log	0.5128	20	0.6577	-0.0081	0.6577	0.8110
No log	0.5641	22	0.7544	0.0647	0.7544	0.8685
No log	0.6154	24	0.8336	0.0078	0.8336	0.9130
No log	0.6667	26	0.8256	0.0698	0.8256	0.9086
No log	0.7179	28	0.7625	0.1605	0.7625	0.8732
No log	0.7692	30	0.6825	0.4167	0.6825	0.8261
No log	0.8205	32	0.7592	0.2263	0.7592	0.8713
No log	0.8718	34	0.6697	0.3535	0.6697	0.8184
No log	0.9231	36	0.5725	-0.0081	0.5725	0.7567
No log	0.9744	38	0.5576	0.0	0.5576	0.7467
No log	1.0256	40	0.5471	-0.0081	0.5471	0.7397
No log	1.0769	42	0.6616	0.2464	0.6616	0.8134
No log	1.1282	44	0.6593	0.2381	0.6593	0.8120
No log	1.1795	46	0.6753	0.2381	0.6753	0.8218
No log	1.2308	48	0.7559	0.2281	0.7559	0.8694
No log	1.2821	50	0.6564	0.2464	0.6564	0.8102
No log	1.3333	52	0.5206	0.0909	0.5206	0.7215
No log	1.3846	54	0.5451	0.0	0.5451	0.7383
No log	1.4359	56	0.5343	-0.0081	0.5343	0.7309
No log	1.4872	58	0.5481	0.3464	0.5481	0.7403
No log	1.5385	60	0.7829	0.1712	0.7829	0.8848
No log	1.5897	62	0.8628	0.1453	0.8628	0.9289
No log	1.6410	64	0.5412	0.3333	0.5412	0.7356
No log	1.6923	66	0.4876	0.0815	0.4876	0.6983
No log	1.7436	68	0.5756	0.3333	0.5756	0.7587
No log	1.7949	70	0.8552	0.1864	0.8552	0.9248
No log	1.8462	72	0.6174	0.3016	0.6174	0.7858
No log	1.8974	74	0.4937	0.0909	0.4937	0.7026
No log	1.9487	76	0.5451	0.1765	0.5451	0.7383
No log	2.0	78	0.5165	0.1642	0.5165	0.7187
No log	2.0513	80	0.7536	0.2554	0.7536	0.8681
No log	2.1026	82	0.8214	0.2263	0.8214	0.9063
No log	2.1538	84	0.5261	0.1888	0.5261	0.7254
No log	2.2051	86	0.5775	0.1206	0.5775	0.7599
No log	2.2564	88	0.5140	0.2318	0.5140	0.7169
No log	2.3077	90	0.6680	0.2607	0.6680	0.8173
No log	2.3590	92	0.6941	0.2637	0.6941	0.8331
No log	2.4103	94	0.4842	0.3007	0.4842	0.6958
No log	2.4615	96	0.5143	0.2208	0.5143	0.7171
No log	2.5128	98	0.4838	0.3766	0.4838	0.6956
No log	2.5641	100	0.6593	0.3271	0.6593	0.8120
No log	2.6154	102	0.5159	0.4894	0.5159	0.7183
No log	2.6667	104	0.8087	0.2258	0.8087	0.8993
No log	2.7179	106	1.0627	0.1126	1.0627	1.0309
No log	2.7692	108	0.9623	0.1378	0.9623	0.9809
No log	2.8205	110	0.5297	0.3878	0.5297	0.7278
No log	2.8718	112	0.5850	0.3623	0.5850	0.7649
No log	2.9231	114	0.5198	0.4051	0.5198	0.7210
No log	2.9744	116	0.4905	0.4146	0.4905	0.7003
No log	3.0256	118	0.5505	0.2393	0.5505	0.7420
No log	3.0769	120	0.5063	0.2105	0.5063	0.7115
No log	3.1282	122	0.5298	0.36	0.5298	0.7279
No log	3.1795	124	0.5995	0.2000	0.5995	0.7743
No log	3.2308	126	0.7198	0.2577	0.7198	0.8484
No log	3.2821	128	0.5329	0.2865	0.5329	0.7300
No log	3.3333	130	0.5976	0.3561	0.5976	0.7730
No log	3.3846	132	0.5505	0.3469	0.5505	0.7419
No log	3.4359	134	0.5723	0.2289	0.5723	0.7565
No log	3.4872	136	0.5584	0.2485	0.5584	0.7473
No log	3.5385	138	0.6117	0.3814	0.6117	0.7821
No log	3.5897	140	0.5720	0.3182	0.5720	0.7563
No log	3.6410	142	0.5964	0.3297	0.5964	0.7722
No log	3.6923	144	0.6051	0.1917	0.6051	0.7779
No log	3.7436	146	0.7445	0.2653	0.7445	0.8628
No log	3.7949	148	0.5849	0.3052	0.5849	0.7648
No log	3.8462	150	0.5779	0.3462	0.5779	0.7602
No log	3.8974	152	0.8398	0.2281	0.8398	0.9164
No log	3.9487	154	0.8749	0.2275	0.8749	0.9354
No log	4.0	156	0.5431	0.3367	0.5431	0.7370
No log	4.0513	158	0.5265	0.2889	0.5265	0.7256
No log	4.1026	160	0.5356	0.2914	0.5356	0.7319
No log	4.1538	162	0.5829	0.2174	0.5829	0.7635
No log	4.2051	164	0.5487	0.3149	0.5487	0.7407
No log	4.2564	166	0.5911	0.2088	0.5911	0.7688
No log	4.3077	168	0.5719	0.2340	0.5719	0.7562
No log	4.3590	170	0.6576	0.3214	0.6576	0.8109
No log	4.4103	172	0.7102	0.2900	0.7102	0.8427
No log	4.4615	174	0.5599	0.3520	0.5599	0.7483
No log	4.5128	176	0.8254	0.2287	0.8254	0.9085
No log	4.5641	178	0.8380	0.2281	0.8380	0.9154
No log	4.6154	180	0.5665	0.2418	0.5665	0.7526
No log	4.6667	182	0.6345	0.2593	0.6345	0.7966
No log	4.7179	184	0.8270	0.1736	0.8270	0.9094
No log	4.7692	186	0.7337	0.2857	0.7337	0.8565
No log	4.8205	188	0.5567	0.1020	0.5567	0.7461
No log	4.8718	190	0.5412	0.2432	0.5412	0.7356
No log	4.9231	192	0.6186	0.2809	0.6186	0.7865
No log	4.9744	194	0.5463	0.3054	0.5463	0.7391
No log	5.0256	196	0.5743	0.3663	0.5743	0.7579
No log	5.0769	198	0.5990	0.3462	0.5990	0.7740
No log	5.1282	200	0.5764	0.3684	0.5764	0.7592
No log	5.1795	202	0.6914	0.3684	0.6914	0.8315
No log	5.2308	204	0.6459	0.3242	0.6459	0.8037
No log	5.2821	206	0.6272	0.3043	0.6272	0.7920
No log	5.3333	208	0.6074	0.3363	0.6074	0.7793
No log	5.3846	210	0.5901	0.3171	0.5901	0.7682
No log	5.4359	212	0.5776	0.2340	0.5776	0.7600
No log	5.4872	214	0.5933	0.2527	0.5933	0.7703
No log	5.5385	216	0.5584	0.2766	0.5584	0.7472
No log	5.5897	218	0.5567	0.2093	0.5567	0.7462
No log	5.6410	220	0.6042	0.2273	0.6042	0.7773
No log	5.6923	222	0.6333	0.2258	0.6333	0.7958
No log	5.7436	224	0.6430	0.2258	0.6430	0.8019
No log	5.7949	226	0.6190	0.1739	0.6190	0.7867
No log	5.8462	228	0.6124	0.3161	0.6124	0.7825
No log	5.8974	230	0.8424	0.2653	0.8424	0.9178
No log	5.9487	232	0.9167	0.2756	0.9167	0.9574
No log	6.0	234	0.7262	0.2857	0.7262	0.8522
No log	6.0513	236	0.5851	0.1515	0.5851	0.7649
No log	6.1026	238	0.6395	0.2577	0.6395	0.7997
No log	6.1538	240	0.6226	0.1209	0.6226	0.7891
No log	6.2051	242	0.6106	0.1186	0.6106	0.7814
No log	6.2564	244	0.6076	0.2941	0.6076	0.7795
No log	6.3077	246	0.6287	0.2653	0.6287	0.7929
No log	6.3590	248	0.6004	0.1345	0.6004	0.7748
No log	6.4103	250	0.6204	0.1648	0.6204	0.7876
No log	6.4615	252	0.6730	0.2079	0.6730	0.8204
No log	6.5128	254	0.6689	0.2079	0.6689	0.8179
No log	6.5641	256	0.6154	0.1765	0.6154	0.7845
No log	6.6154	258	0.6903	0.4286	0.6903	0.8308
No log	6.6667	260	0.6738	0.4286	0.6738	0.8208
No log	6.7179	262	0.5892	0.2607	0.5892	0.7676
No log	6.7692	264	0.5986	0.2941	0.5986	0.7737
No log	6.8205	266	0.6382	0.2917	0.6382	0.7989
No log	6.8718	268	0.5861	0.2865	0.5861	0.7655
No log	6.9231	270	0.5543	0.25	0.5543	0.7445
No log	6.9744	272	0.5451	0.25	0.5451	0.7383
No log	7.0256	274	0.5310	0.2457	0.5310	0.7287
No log	7.0769	276	0.5244	0.2457	0.5244	0.7241
No log	7.1282	278	0.5187	0.1807	0.5187	0.7202
No log	7.1795	280	0.5180	0.1716	0.5180	0.7197
No log	7.2308	282	0.5516	0.3103	0.5516	0.7427
No log	7.2821	284	0.5943	0.3585	0.5943	0.7709
No log	7.3333	286	0.5729	0.3010	0.5729	0.7569
No log	7.3846	288	0.5407	0.1813	0.5407	0.7353
No log	7.4359	290	0.5842	0.2967	0.5842	0.7643
No log	7.4872	292	0.5986	0.2542	0.5986	0.7737
No log	7.5385	294	0.5822	0.2457	0.5822	0.7630
No log	7.5897	296	0.5944	0.2323	0.5944	0.7710
No log	7.6410	298	0.6361	0.3077	0.6361	0.7975
No log	7.6923	300	0.6059	0.2653	0.6059	0.7784
No log	7.7436	302	0.5832	0.2265	0.5832	0.7637
No log	7.7949	304	0.6126	0.2090	0.6126	0.7827
No log	7.8462	306	0.6148	0.2090	0.6148	0.7841
No log	7.8974	308	0.5860	0.2096	0.5860	0.7655
No log	7.9487	310	0.5615	0.2516	0.5615	0.7493
No log	8.0	312	0.5529	0.1899	0.5529	0.7436
No log	8.0513	314	0.5474	0.1373	0.5474	0.7399
No log	8.1026	316	0.5444	0.1467	0.5444	0.7379
No log	8.1538	318	0.5491	0.2096	0.5491	0.7410
No log	8.2051	320	0.5569	0.2096	0.5569	0.7462
No log	8.2564	322	0.5648	0.2093	0.5648	0.7516
No log	8.3077	324	0.5772	0.2542	0.5772	0.7597
No log	8.3590	326	0.5554	0.1543	0.5554	0.7453
No log	8.4103	328	0.5378	0.2000	0.5378	0.7333
No log	8.4615	330	0.5313	0.2000	0.5313	0.7289
No log	8.5128	332	0.5275	0.2393	0.5275	0.7263
No log	8.5641	334	0.5230	0.2393	0.5230	0.7232
No log	8.6154	336	0.5204	0.2000	0.5204	0.7214
No log	8.6667	338	0.5315	0.2593	0.5315	0.7290
No log	8.7179	340	0.5650	0.2626	0.5650	0.7517
No log	8.7692	342	0.5702	0.2727	0.5702	0.7551
No log	8.8205	344	0.5455	0.2542	0.5455	0.7386
No log	8.8718	346	0.5204	0.2000	0.5204	0.7214
No log	8.9231	348	0.5247	0.3446	0.5247	0.7244
No log	8.9744	350	0.5338	0.3016	0.5338	0.7306
No log	9.0256	352	0.5323	0.3016	0.5323	0.7296
No log	9.0769	354	0.5244	0.3446	0.5244	0.7241
No log	9.1282	356	0.5184	0.3216	0.5184	0.7200
No log	9.1795	358	0.5222	0.2593	0.5222	0.7226
No log	9.2308	360	0.5274	0.3023	0.5274	0.7262
No log	9.2821	362	0.5339	0.3023	0.5339	0.7307
No log	9.3333	364	0.5372	0.3023	0.5372	0.7330
No log	9.3846	366	0.5442	0.2542	0.5442	0.7377
No log	9.4359	368	0.5485	0.2542	0.5485	0.7406
No log	9.4872	370	0.5454	0.2542	0.5454	0.7385
No log	9.5385	372	0.5345	0.3023	0.5345	0.7311
No log	9.5897	374	0.5280	0.3023	0.5280	0.7266
No log	9.6410	376	0.5253	0.2593	0.5253	0.7248
No log	9.6923	378	0.5244	0.3455	0.5244	0.7241
No log	9.7436	380	0.5250	0.3455	0.5250	0.7246
No log	9.7949	382	0.5260	0.3455	0.5260	0.7253
No log	9.8462	384	0.5264	0.2593	0.5264	0.7256
No log	9.8974	386	0.5280	0.3054	0.5280	0.7266
No log	9.9487	388	0.5298	0.3023	0.5298	0.7279
No log	10.0	390	0.5306	0.3023	0.5306	0.7284

Framework versions

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