ArabicNewSplits6_WithDuplicationsForScore5_FineTuningAraBERT_run1_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: 0.7253
• Qwk: 0.7198
• Mse: 0.7253
• Rmse: 0.8517

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	5.3545	0.0098	5.3545	2.3140
No log	0.1111	4	3.3186	0.0722	3.3186	1.8217
No log	0.1667	6	2.1358	0.0447	2.1358	1.4614
No log	0.2222	8	1.4223	0.1659	1.4223	1.1926
No log	0.2778	10	1.1264	0.4044	1.1264	1.0613
No log	0.3333	12	1.1149	0.3590	1.1149	1.0559
No log	0.3889	14	1.3609	0.2109	1.3609	1.1666
No log	0.4444	16	1.2198	0.3739	1.2198	1.1044
No log	0.5	18	1.0571	0.4176	1.0571	1.0282
No log	0.5556	20	1.0321	0.4398	1.0321	1.0159
No log	0.6111	22	0.9229	0.5151	0.9229	0.9607
No log	0.6667	24	0.9116	0.4821	0.9116	0.9548
No log	0.7222	26	1.3568	0.3041	1.3568	1.1648
No log	0.7778	28	2.2653	0.2337	2.2653	1.5051
No log	0.8333	30	2.6818	0.1792	2.6818	1.6376
No log	0.8889	32	2.4482	0.2091	2.4482	1.5647
No log	0.9444	34	1.6172	0.2672	1.6172	1.2717
No log	1.0	36	1.0494	0.4167	1.0494	1.0244
No log	1.0556	38	0.7201	0.6202	0.7201	0.8486
No log	1.1111	40	0.7423	0.6159	0.7423	0.8616
No log	1.1667	42	0.7054	0.6416	0.7054	0.8399
No log	1.2222	44	1.0017	0.5369	1.0017	1.0008
No log	1.2778	46	1.2822	0.4395	1.2822	1.1324
No log	1.3333	48	1.2306	0.5288	1.2306	1.1093
No log	1.3889	50	0.9036	0.5911	0.9036	0.9506
No log	1.4444	52	0.7406	0.6891	0.7406	0.8606
No log	1.5	54	0.9106	0.6897	0.9106	0.9542
No log	1.5556	56	0.8784	0.6628	0.8784	0.9372
No log	1.6111	58	0.6518	0.7208	0.6518	0.8073
No log	1.6667	60	0.6406	0.6715	0.6406	0.8004
No log	1.7222	62	0.8110	0.6137	0.8110	0.9005
No log	1.7778	64	0.7951	0.6567	0.7951	0.8917
No log	1.8333	66	0.6441	0.6960	0.6441	0.8026
No log	1.8889	68	0.6289	0.7278	0.6289	0.7930
No log	1.9444	70	0.6996	0.6978	0.6996	0.8364
No log	2.0	72	0.6661	0.7455	0.6661	0.8161
No log	2.0556	74	0.6198	0.7345	0.6198	0.7873
No log	2.1111	76	0.6826	0.6754	0.6826	0.8262
No log	2.1667	78	0.7482	0.6553	0.7482	0.8650
No log	2.2222	80	0.9125	0.6106	0.9125	0.9552
No log	2.2778	82	0.9968	0.6020	0.9968	0.9984
No log	2.3333	84	0.7818	0.5967	0.7818	0.8842
No log	2.3889	86	0.6302	0.7340	0.6302	0.7938
No log	2.4444	88	0.7321	0.7033	0.7321	0.8556
No log	2.5	90	0.7895	0.6964	0.7895	0.8885
No log	2.5556	92	0.7145	0.7055	0.7145	0.8453
No log	2.6111	94	0.6224	0.7322	0.6224	0.7889
No log	2.6667	96	0.6976	0.6628	0.6976	0.8352
No log	2.7222	98	0.7955	0.6589	0.7955	0.8919
No log	2.7778	100	0.7242	0.6853	0.7242	0.8510
No log	2.8333	102	0.6410	0.7465	0.6410	0.8006
No log	2.8889	104	0.7691	0.7072	0.7691	0.8770
No log	2.9444	106	0.8555	0.7099	0.8555	0.9249
No log	3.0	108	0.9099	0.6791	0.9099	0.9539
No log	3.0556	110	0.7619	0.7214	0.7619	0.8729
No log	3.1111	112	0.6542	0.7039	0.6542	0.8088
No log	3.1667	114	0.6594	0.7011	0.6594	0.8120
No log	3.2222	116	0.6574	0.7143	0.6574	0.8108
No log	3.2778	118	0.6435	0.7038	0.6435	0.8022
No log	3.3333	120	0.7063	0.7219	0.7063	0.8404
No log	3.3889	122	0.7539	0.7387	0.7539	0.8683
No log	3.4444	124	0.8341	0.7040	0.8341	0.9133
No log	3.5	126	0.7740	0.7280	0.7740	0.8798
No log	3.5556	128	0.6689	0.7375	0.6689	0.8179
No log	3.6111	130	0.6650	0.7410	0.6650	0.8155
No log	3.6667	132	0.7165	0.7018	0.7165	0.8464
No log	3.7222	134	0.7270	0.6789	0.7270	0.8526
No log	3.7778	136	0.6731	0.7003	0.6731	0.8204
No log	3.8333	138	0.6562	0.7231	0.6562	0.8101
No log	3.8889	140	0.6631	0.7277	0.6631	0.8143
No log	3.9444	142	0.6207	0.7513	0.6207	0.7879
No log	4.0	144	0.6302	0.6798	0.6302	0.7938
No log	4.0556	146	0.7164	0.6617	0.7164	0.8464
No log	4.1111	148	0.7337	0.6490	0.7337	0.8566
No log	4.1667	150	0.6653	0.6640	0.6653	0.8157
No log	4.2222	152	0.6319	0.7351	0.6319	0.7949
No log	4.2778	154	0.6695	0.7283	0.6695	0.8182
No log	4.3333	156	0.7228	0.7268	0.7228	0.8502
No log	4.3889	158	0.7291	0.7250	0.7291	0.8539
No log	4.4444	160	0.6824	0.7332	0.6824	0.8261
No log	4.5	162	0.6606	0.7265	0.6606	0.8128
No log	4.5556	164	0.6532	0.7162	0.6532	0.8082
No log	4.6111	166	0.6745	0.7283	0.6745	0.8213
No log	4.6667	168	0.7082	0.7131	0.7082	0.8416
No log	4.7222	170	0.6898	0.6908	0.6898	0.8305
No log	4.7778	172	0.6549	0.7185	0.6549	0.8092
No log	4.8333	174	0.6491	0.7223	0.6491	0.8057
No log	4.8889	176	0.6686	0.7056	0.6686	0.8177
No log	4.9444	178	0.7028	0.7108	0.7028	0.8383
No log	5.0	180	0.7159	0.7201	0.7159	0.8461
No log	5.0556	182	0.7345	0.7205	0.7345	0.8570
No log	5.1111	184	0.7394	0.6994	0.7394	0.8599
No log	5.1667	186	0.7377	0.7045	0.7377	0.8589
No log	5.2222	188	0.7022	0.6969	0.7022	0.8380
No log	5.2778	190	0.6900	0.7028	0.6900	0.8307
No log	5.3333	192	0.7027	0.6925	0.7027	0.8382
No log	5.3889	194	0.7124	0.6918	0.7124	0.8440
No log	5.4444	196	0.7016	0.6955	0.7016	0.8376
No log	5.5	198	0.7106	0.6955	0.7106	0.8429
No log	5.5556	200	0.7377	0.6918	0.7377	0.8589
No log	5.6111	202	0.7554	0.6892	0.7554	0.8691
No log	5.6667	204	0.7694	0.6871	0.7694	0.8772
No log	5.7222	206	0.7613	0.7155	0.7613	0.8725
No log	5.7778	208	0.7722	0.7044	0.7722	0.8787
No log	5.8333	210	0.7812	0.6936	0.7812	0.8838
No log	5.8889	212	0.7925	0.7068	0.7925	0.8902
No log	5.9444	214	0.8405	0.6907	0.8405	0.9168
No log	6.0	216	0.8518	0.6889	0.8518	0.9229
No log	6.0556	218	0.8035	0.6997	0.8035	0.8964
No log	6.1111	220	0.7344	0.7097	0.7344	0.8570
No log	6.1667	222	0.7153	0.7035	0.7153	0.8458
No log	6.2222	224	0.7065	0.6668	0.7065	0.8405
No log	6.2778	226	0.7114	0.6709	0.7114	0.8435
No log	6.3333	228	0.7372	0.7223	0.7372	0.8586
No log	6.3889	230	0.8211	0.7094	0.8211	0.9061
No log	6.4444	232	0.8939	0.7048	0.8939	0.9455
No log	6.5	234	0.9178	0.6998	0.9178	0.9580
No log	6.5556	236	0.8540	0.7018	0.8540	0.9241
No log	6.6111	238	0.8013	0.7177	0.8013	0.8951
No log	6.6667	240	0.7801	0.7165	0.7801	0.8832
No log	6.7222	242	0.7384	0.7157	0.7384	0.8593
No log	6.7778	244	0.6975	0.7065	0.6975	0.8352
No log	6.8333	246	0.6646	0.6954	0.6646	0.8152
No log	6.8889	248	0.6462	0.7172	0.6462	0.8039
No log	6.9444	250	0.6436	0.7058	0.6436	0.8023
No log	7.0	252	0.6582	0.6901	0.6582	0.8113
No log	7.0556	254	0.6808	0.6986	0.6808	0.8251
No log	7.1111	256	0.7052	0.7212	0.7052	0.8398
No log	7.1667	258	0.6939	0.7098	0.6939	0.8330
No log	7.2222	260	0.6767	0.7211	0.6767	0.8226
No log	7.2778	262	0.6785	0.7260	0.6785	0.8237
No log	7.3333	264	0.6873	0.7155	0.6873	0.8290
No log	7.3889	266	0.6942	0.7155	0.6942	0.8332
No log	7.4444	268	0.7025	0.7058	0.7025	0.8381
No log	7.5	270	0.7065	0.7052	0.7065	0.8406
No log	7.5556	272	0.6950	0.7260	0.6950	0.8337
No log	7.6111	274	0.6853	0.7022	0.6853	0.8279
No log	7.6667	276	0.6934	0.6865	0.6934	0.8327
No log	7.7222	278	0.7297	0.6509	0.7297	0.8542
No log	7.7778	280	0.7369	0.6605	0.7369	0.8584
No log	7.8333	282	0.7128	0.6639	0.7128	0.8443
No log	7.8889	284	0.6972	0.6901	0.6972	0.8350
No log	7.9444	286	0.6998	0.6768	0.6998	0.8366
No log	8.0	288	0.7233	0.7052	0.7233	0.8505
No log	8.0556	290	0.7385	0.6878	0.7385	0.8594
No log	8.1111	292	0.7372	0.6920	0.7372	0.8586
No log	8.1667	294	0.7247	0.6854	0.7247	0.8513
No log	8.2222	296	0.7106	0.6745	0.7106	0.8430
No log	8.2778	298	0.7055	0.6727	0.7055	0.8399
No log	8.3333	300	0.7040	0.7111	0.7040	0.8391
No log	8.3889	302	0.7033	0.7075	0.7033	0.8386
No log	8.4444	304	0.6999	0.6725	0.6999	0.8366
No log	8.5	306	0.7083	0.6748	0.7083	0.8416
No log	8.5556	308	0.7178	0.6680	0.7178	0.8472
No log	8.6111	310	0.7312	0.6741	0.7312	0.8551
No log	8.6667	312	0.7352	0.6968	0.7352	0.8574
No log	8.7222	314	0.7267	0.6741	0.7267	0.8525
No log	8.7778	316	0.7163	0.6748	0.7163	0.8463
No log	8.8333	318	0.7124	0.6786	0.7124	0.8441
No log	8.8889	320	0.7111	0.6870	0.7111	0.8433
No log	8.9444	322	0.7140	0.6906	0.7140	0.8450
No log	9.0	324	0.7158	0.6817	0.7158	0.8461
No log	9.0556	326	0.7184	0.7049	0.7184	0.8476
No log	9.1111	328	0.7209	0.7120	0.7209	0.8490
No log	9.1667	330	0.7208	0.7120	0.7208	0.8490
No log	9.2222	332	0.7213	0.7120	0.7213	0.8493
No log	9.2778	334	0.7211	0.7120	0.7211	0.8491
No log	9.3333	336	0.7214	0.7175	0.7214	0.8494
No log	9.3889	338	0.7219	0.7175	0.7219	0.8496
No log	9.4444	340	0.7256	0.7117	0.7256	0.8518
No log	9.5	342	0.7254	0.7117	0.7254	0.8517
No log	9.5556	344	0.7236	0.7117	0.7236	0.8506
No log	9.6111	346	0.7218	0.7117	0.7218	0.8496
No log	9.6667	348	0.7225	0.7117	0.7225	0.8500
No log	9.7222	350	0.7257	0.7172	0.7257	0.8519
No log	9.7778	352	0.7270	0.7198	0.7270	0.8526
No log	9.8333	354	0.7271	0.7158	0.7271	0.8527
No log	9.8889	356	0.7263	0.7158	0.7263	0.8522
No log	9.9444	358	0.7256	0.7198	0.7256	0.8518
No log	10.0	360	0.7253	0.7198	0.7253	0.8517

Framework versions

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