ArabicNewSplits5_FineTuningAraBERT_run2_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: 0.8373
• Qwk: 0.2243
• Mse: 0.8373
• Rmse: 0.9150

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	3.3228	-0.0138	3.3228	1.8229
No log	0.1081	4	1.7460	-0.0101	1.7460	1.3213
No log	0.1622	6	1.9001	0.0455	1.9001	1.3784
No log	0.2162	8	1.4987	0.0255	1.4987	1.2242
No log	0.2703	10	1.0831	0.0	1.0831	1.0407
No log	0.3243	12	0.9396	0.0078	0.9396	0.9693
No log	0.3784	14	0.7893	-0.0149	0.7893	0.8884
No log	0.4324	16	0.8611	-0.0133	0.8611	0.9280
No log	0.4865	18	0.9873	0.0078	0.9873	0.9936
No log	0.5405	20	1.0821	0.0038	1.0821	1.0402
No log	0.5946	22	1.1285	0.0	1.1285	1.0623
No log	0.6486	24	0.8970	0.0794	0.8970	0.9471
No log	0.7027	26	0.7145	-0.1242	0.7145	0.8453
No log	0.7568	28	0.6507	0.1008	0.6507	0.8066
No log	0.8108	30	0.6794	0.1195	0.6794	0.8242
No log	0.8649	32	0.8965	0.1934	0.8965	0.9468
No log	0.9189	34	1.1337	0.0388	1.1337	1.0648
No log	0.9730	36	1.1319	0.0745	1.1319	1.0639
No log	1.0270	38	0.9673	0.0745	0.9673	0.9835
No log	1.0811	40	0.8763	0.1276	0.8763	0.9361
No log	1.1351	42	0.8434	0.1169	0.8434	0.9184
No log	1.1892	44	0.7885	0.0588	0.7885	0.8880
No log	1.2432	46	0.6998	-0.0196	0.6998	0.8366
No log	1.2973	48	0.7110	-0.0133	0.7110	0.8432
No log	1.3514	50	0.8738	0.0769	0.8738	0.9347
No log	1.4054	52	1.1467	0.1008	1.1467	1.0708
No log	1.4595	54	1.0535	0.1111	1.0535	1.0264
No log	1.5135	56	0.9304	0.1504	0.9304	0.9646
No log	1.5676	58	0.7599	-0.1200	0.7599	0.8717
No log	1.6216	60	0.7550	-0.0909	0.7550	0.8689
No log	1.6757	62	0.6718	-0.0233	0.6718	0.8196
No log	1.7297	64	0.5882	0.0	0.5882	0.7670
No log	1.7838	66	0.8074	0.2068	0.8074	0.8985
No log	1.8378	68	0.9995	0.0698	0.9995	0.9997
No log	1.8919	70	0.8373	0.1276	0.8372	0.9150
No log	1.9459	72	0.6820	0.1746	0.6820	0.8259
No log	2.0	74	0.6427	0.0952	0.6427	0.8017
No log	2.0541	76	0.6701	0.1724	0.6701	0.8186
No log	2.1081	78	0.7041	0.0667	0.7041	0.8391
No log	2.1622	80	0.6350	-0.0068	0.6350	0.7969
No log	2.2162	82	0.5918	0.0222	0.5918	0.7693
No log	2.2703	84	0.5848	-0.0159	0.5848	0.7647
No log	2.3243	86	0.5763	0.0303	0.5763	0.7592
No log	2.3784	88	0.6304	0.1364	0.6304	0.7940
No log	2.4324	90	0.6000	0.1908	0.6000	0.7746
No log	2.4865	92	0.6079	-0.0303	0.6079	0.7797
No log	2.5405	94	0.6700	-0.0072	0.6700	0.8185
No log	2.5946	96	0.5950	0.1145	0.5950	0.7713
No log	2.6486	98	0.5173	0.2683	0.5173	0.7193
No log	2.7027	100	0.5423	0.3191	0.5423	0.7364
No log	2.7568	102	0.4815	0.2418	0.4815	0.6939
No log	2.8108	104	0.7124	0.2323	0.7124	0.8440
No log	2.8649	106	0.8444	0.1928	0.8444	0.9189
No log	2.9189	108	0.8926	0.1347	0.8926	0.9448
No log	2.9730	110	0.8258	0.1644	0.8258	0.9087
No log	3.0270	112	0.6588	0.2577	0.6588	0.8117
No log	3.0811	114	0.5866	0.2670	0.5866	0.7659
No log	3.1351	116	0.6912	0.2780	0.6912	0.8314
No log	3.1892	118	0.6796	0.2780	0.6796	0.8244
No log	3.2432	120	0.6278	0.3103	0.6278	0.7923
No log	3.2973	122	0.6430	0.3103	0.6430	0.8019
No log	3.3514	124	0.7150	0.2838	0.7150	0.8456
No log	3.4054	126	0.6517	0.3645	0.6517	0.8073
No log	3.4595	128	0.9076	0.2314	0.9076	0.9527
No log	3.5135	130	1.1111	0.1278	1.1111	1.0541
No log	3.5676	132	0.8947	0.2000	0.8947	0.9459
No log	3.6216	134	0.6384	0.3028	0.6384	0.7990
No log	3.6757	136	0.6798	0.3462	0.6798	0.8245
No log	3.7297	138	0.6271	0.3561	0.6271	0.7919
No log	3.7838	140	0.5352	0.3862	0.5352	0.7316
No log	3.8378	142	0.7091	0.3242	0.7091	0.8421
No log	3.8919	144	0.9922	0.1938	0.9922	0.9961
No log	3.9459	146	1.0232	0.2000	1.0232	1.0115
No log	4.0	148	0.7415	0.2554	0.7415	0.8611
No log	4.0541	150	0.4974	0.4051	0.4974	0.7053
No log	4.1081	152	0.4976	0.3939	0.4976	0.7054
No log	4.1622	154	0.6114	0.3143	0.6114	0.7819
No log	4.2162	156	0.9481	0.2180	0.9481	0.9737
No log	4.2703	158	1.0246	0.2177	1.0246	1.0122
No log	4.3243	160	0.8052	0.2063	0.8052	0.8973
No log	4.3784	162	0.5751	0.5365	0.5751	0.7584
No log	4.4324	164	0.5850	0.5130	0.5850	0.7649
No log	4.4865	166	0.5925	0.4828	0.5925	0.7698
No log	4.5405	168	0.8326	0.2062	0.8326	0.9125
No log	4.5946	170	1.3018	0.1683	1.3018	1.1410
No log	4.6486	172	1.3838	0.1429	1.3838	1.1763
No log	4.7027	174	1.0556	0.1880	1.0556	1.0274
No log	4.7568	176	0.8028	0.2782	0.8028	0.8960
No log	4.8108	178	0.7407	0.3735	0.7407	0.8607
No log	4.8649	180	0.8111	0.3030	0.8111	0.9006
No log	4.9189	182	0.8750	0.2381	0.8750	0.9354
No log	4.9730	184	0.9151	0.2374	0.9151	0.9566
No log	5.0270	186	0.9284	0.2126	0.9284	0.9635
No log	5.0811	188	0.6960	0.3333	0.6960	0.8343
No log	5.1351	190	0.5590	0.4694	0.5590	0.7477
No log	5.1892	192	0.5397	0.4694	0.5397	0.7346
No log	5.2432	194	0.6151	0.3333	0.6151	0.7843
No log	5.2973	196	0.8430	0.2208	0.8430	0.9181
No log	5.3514	198	0.8419	0.1855	0.8419	0.9176
No log	5.4054	200	0.6665	0.3035	0.6665	0.8164
No log	5.4595	202	0.5276	0.4231	0.5276	0.7264
No log	5.5135	204	0.5071	0.4450	0.5071	0.7121
No log	5.5676	206	0.5709	0.4286	0.5709	0.7556
No log	5.6216	208	0.6769	0.2850	0.6769	0.8227
No log	5.6757	210	0.8019	0.1504	0.8019	0.8955
No log	5.7297	212	0.7431	0.2696	0.7431	0.8621
No log	5.7838	214	0.6046	0.3702	0.6046	0.7776
No log	5.8378	216	0.6109	0.3702	0.6109	0.7816
No log	5.8919	218	0.6395	0.3793	0.6395	0.7997
No log	5.9459	220	0.7905	0.2618	0.7905	0.8891
No log	6.0	222	0.8957	0.2131	0.8957	0.9464
No log	6.0541	224	0.8020	0.1933	0.8020	0.8956
No log	6.1081	226	0.7418	0.2531	0.7418	0.8613
No log	6.1622	228	0.7222	0.2348	0.7222	0.8498
No log	6.2162	230	0.8771	0.2131	0.8771	0.9365
No log	6.2703	232	0.8781	0.1870	0.8781	0.9371
No log	6.3243	234	0.8598	0.2191	0.8598	0.9273
No log	6.3784	236	0.7847	0.2199	0.7847	0.8859
No log	6.4324	238	0.7300	0.1861	0.7300	0.8544
No log	6.4865	240	0.6614	0.2963	0.6614	0.8133
No log	6.5405	242	0.6765	0.2941	0.6765	0.8225
No log	6.5946	244	0.7180	0.1864	0.7180	0.8473
No log	6.6486	246	0.6973	0.2920	0.6973	0.8350
No log	6.7027	248	0.6792	0.2986	0.6792	0.8241
No log	6.7568	250	0.7133	0.3128	0.7133	0.8445
No log	6.8108	252	0.7731	0.2203	0.7731	0.8793
No log	6.8649	254	1.0253	0.2456	1.0253	1.0126
No log	6.9189	256	1.1846	0.25	1.1846	1.0884
No log	6.9730	258	1.1397	0.25	1.1397	1.0676
No log	7.0270	260	0.9374	0.2177	0.9374	0.9682
No log	7.0811	262	0.7859	0.3036	0.7859	0.8865
No log	7.1351	264	0.6945	0.2961	0.6945	0.8333
No log	7.1892	266	0.6647	0.3004	0.6647	0.8153
No log	7.2432	268	0.6661	0.3043	0.6661	0.8161
No log	7.2973	270	0.7200	0.2838	0.7200	0.8485
No log	7.3514	272	0.7821	0.1554	0.7821	0.8844
No log	7.4054	274	0.8302	0.1877	0.8302	0.9112
No log	7.4595	276	0.9197	0.2464	0.9197	0.9590
No log	7.5135	278	0.9270	0.2527	0.9270	0.9628
No log	7.5676	280	0.8131	0.2180	0.8131	0.9017
No log	7.6216	282	0.6513	0.3391	0.6513	0.8071
No log	7.6757	284	0.5490	0.4178	0.5490	0.7409
No log	7.7297	286	0.5195	0.3725	0.5195	0.7207
No log	7.7838	288	0.5611	0.4178	0.5611	0.7491
No log	7.8378	290	0.6826	0.2579	0.6826	0.8262
No log	7.8919	292	0.7522	0.2542	0.7522	0.8673
No log	7.9459	294	0.7335	0.2208	0.7335	0.8564
No log	8.0	296	0.6380	0.3645	0.6380	0.7988
No log	8.0541	298	0.5480	0.3333	0.5480	0.7403
No log	8.1081	300	0.5333	0.3131	0.5333	0.7303
No log	8.1622	302	0.5871	0.3663	0.5871	0.7662
No log	8.2162	304	0.7221	0.2208	0.7221	0.8497
No log	8.2703	306	0.9411	0.2527	0.9411	0.9701
No log	8.3243	308	1.0538	0.2518	1.0538	1.0265
No log	8.3784	310	1.0486	0.2518	1.0486	1.0240
No log	8.4324	312	0.9688	0.2527	0.9688	0.9843
No log	8.4865	314	0.8629	0.1877	0.8629	0.9289
No log	8.5405	316	0.7488	0.2203	0.7488	0.8654
No log	8.5946	318	0.6280	0.3333	0.6280	0.7925
No log	8.6486	320	0.5754	0.3803	0.5754	0.7585
No log	8.7027	322	0.5777	0.4074	0.5777	0.7600
No log	8.7568	324	0.6219	0.4081	0.6219	0.7886
No log	8.8108	326	0.6937	0.2838	0.6937	0.8329
No log	8.8649	328	0.7934	0.1875	0.7934	0.8907
No log	8.9189	330	0.8777	0.2239	0.8777	0.9368
No log	8.9730	332	0.9047	0.2239	0.9047	0.9511
No log	9.0270	334	0.8976	0.2239	0.8976	0.9474
No log	9.0811	336	0.8469	0.2243	0.8469	0.9203
No log	9.1351	338	0.7698	0.2191	0.7698	0.8774
No log	9.1892	340	0.6877	0.3214	0.6877	0.8293
No log	9.2432	342	0.6373	0.2897	0.6373	0.7983
No log	9.2973	344	0.6001	0.3367	0.6001	0.7747
No log	9.3514	346	0.5834	0.3663	0.5834	0.7638
No log	9.4054	348	0.5750	0.3663	0.5750	0.7583
No log	9.4595	350	0.5853	0.3367	0.5853	0.7651
No log	9.5135	352	0.6131	0.3333	0.6131	0.7830
No log	9.5676	354	0.6565	0.2877	0.6565	0.8102
No log	9.6216	356	0.7085	0.3303	0.7085	0.8417
No log	9.6757	358	0.7622	0.2191	0.7622	0.8730
No log	9.7297	360	0.7981	0.1875	0.7981	0.8934
No log	9.7838	362	0.8210	0.1875	0.8210	0.9061
No log	9.8378	364	0.8336	0.2248	0.8336	0.9130
No log	9.8919	366	0.8375	0.2243	0.8375	0.9152
No log	9.9459	368	0.8375	0.2243	0.8375	0.9152
No log	10.0	370	0.8373	0.2243	0.8373	0.9150

Framework versions

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