ArabicNewSplits6_FineTuningAraBERT_run1_AugV5_k10_task5_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: 0.7400
• Qwk: 0.7168
• Mse: 0.7400
• Rmse: 0.8602

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	2.1832	0.0379	2.1832	1.4776
No log	0.1026	4	1.6201	0.1595	1.6201	1.2728
No log	0.1538	6	1.2888	0.2264	1.2888	1.1352
No log	0.2051	8	1.4053	0.2423	1.4053	1.1855
No log	0.2564	10	1.4438	0.3318	1.4438	1.2016
No log	0.3077	12	1.4594	0.3145	1.4594	1.2081
No log	0.3590	14	1.4014	0.2445	1.4014	1.1838
No log	0.4103	16	1.3826	0.1672	1.3826	1.1758
No log	0.4615	18	1.4265	0.2256	1.4265	1.1944
No log	0.5128	20	1.3873	0.1523	1.3873	1.1779
No log	0.5641	22	1.3365	0.1216	1.3365	1.1561
No log	0.6154	24	1.3018	0.1216	1.3018	1.1409
No log	0.6667	26	1.3047	0.1523	1.3047	1.1422
No log	0.7179	28	1.2884	0.1961	1.2884	1.1351
No log	0.7692	30	1.2581	0.2256	1.2581	1.1217
No log	0.8205	32	1.2769	0.2736	1.2769	1.1300
No log	0.8718	34	1.2657	0.3645	1.2657	1.1250
No log	0.9231	36	1.2289	0.4031	1.2289	1.1086
No log	0.9744	38	1.1289	0.4112	1.1289	1.0625
No log	1.0256	40	1.0606	0.3820	1.0606	1.0299
No log	1.0769	42	1.0274	0.4033	1.0274	1.0136
No log	1.1282	44	1.0035	0.4162	1.0035	1.0017
No log	1.1795	46	0.9672	0.4847	0.9672	0.9835
No log	1.2308	48	0.9318	0.5453	0.9318	0.9653
No log	1.2821	50	0.9294	0.5562	0.9294	0.9640
No log	1.3333	52	0.8441	0.6111	0.8441	0.9188
No log	1.3846	54	0.8103	0.6552	0.8103	0.9002
No log	1.4359	56	0.7674	0.6735	0.7674	0.8760
No log	1.4872	58	0.7425	0.6847	0.7425	0.8617
No log	1.5385	60	0.7187	0.6922	0.7187	0.8478
No log	1.5897	62	0.7116	0.7157	0.7116	0.8436
No log	1.6410	64	0.7102	0.7249	0.7102	0.8427
No log	1.6923	66	0.6935	0.7213	0.6935	0.8328
No log	1.7436	68	0.7133	0.7121	0.7133	0.8445
No log	1.7949	70	0.7720	0.7098	0.7720	0.8786
No log	1.8462	72	1.0255	0.6403	1.0255	1.0127
No log	1.8974	74	1.1067	0.5470	1.1067	1.0520
No log	1.9487	76	0.9338	0.5944	0.9338	0.9664
No log	2.0	78	0.7586	0.6788	0.7586	0.8710
No log	2.0513	80	0.7481	0.6767	0.7481	0.8650
No log	2.1026	82	0.7948	0.6473	0.7948	0.8915
No log	2.1538	84	0.9945	0.5106	0.9945	0.9972
No log	2.2051	86	1.1933	0.5089	1.1933	1.0924
No log	2.2564	88	1.1281	0.5474	1.1281	1.0621
No log	2.3077	90	0.9199	0.5534	0.9199	0.9591
No log	2.3590	92	0.7691	0.6538	0.7691	0.8770
No log	2.4103	94	0.7461	0.6227	0.7461	0.8638
No log	2.4615	96	0.7423	0.6532	0.7423	0.8616
No log	2.5128	98	0.7370	0.6695	0.7370	0.8585
No log	2.5641	100	0.7197	0.6573	0.7197	0.8484
No log	2.6154	102	0.7617	0.6706	0.7617	0.8727
No log	2.6667	104	0.7371	0.7020	0.7371	0.8585
No log	2.7179	106	0.7541	0.7030	0.7541	0.8684
No log	2.7692	108	0.7398	0.7035	0.7398	0.8601
No log	2.8205	110	0.6906	0.7174	0.6906	0.8310
No log	2.8718	112	0.6856	0.7042	0.6856	0.8280
No log	2.9231	114	0.6862	0.7237	0.6862	0.8284
No log	2.9744	116	0.8663	0.6526	0.8663	0.9308
No log	3.0256	118	1.0808	0.5897	1.0808	1.0396
No log	3.0769	120	1.0175	0.6074	1.0175	1.0087
No log	3.1282	122	0.8164	0.6722	0.8164	0.9036
No log	3.1795	124	0.6849	0.7531	0.6849	0.8276
No log	3.2308	126	0.6777	0.7569	0.6777	0.8233
No log	3.2821	128	0.7734	0.7062	0.7734	0.8795
No log	3.3333	130	0.9628	0.6163	0.9628	0.9812
No log	3.3846	132	0.9503	0.6104	0.9503	0.9748
No log	3.4359	134	0.7939	0.6985	0.7939	0.8910
No log	3.4872	136	0.6977	0.7743	0.6977	0.8353
No log	3.5385	138	0.7155	0.7644	0.7155	0.8459
No log	3.5897	140	0.7868	0.6796	0.7868	0.8870
No log	3.6410	142	0.8441	0.6521	0.8441	0.9188
No log	3.6923	144	0.9031	0.6465	0.9031	0.9503
No log	3.7436	146	0.8537	0.6609	0.8537	0.9240
No log	3.7949	148	0.7894	0.6965	0.7894	0.8885
No log	3.8462	150	0.7144	0.7517	0.7144	0.8453
No log	3.8974	152	0.6597	0.7747	0.6597	0.8122
No log	3.9487	154	0.6561	0.7715	0.6561	0.8100
No log	4.0	156	0.7499	0.7423	0.7499	0.8660
No log	4.0513	158	0.7807	0.7106	0.7807	0.8835
No log	4.1026	160	0.7160	0.7570	0.7160	0.8462
No log	4.1538	162	0.6387	0.7815	0.6387	0.7992
No log	4.2051	164	0.6363	0.7815	0.6363	0.7977
No log	4.2564	166	0.6342	0.7858	0.6342	0.7964
No log	4.3077	168	0.6129	0.7589	0.6129	0.7829
No log	4.3590	170	0.6084	0.7548	0.6084	0.7800
No log	4.4103	172	0.6608	0.7528	0.6608	0.8129
No log	4.4615	174	0.7203	0.7371	0.7203	0.8487
No log	4.5128	176	0.6645	0.7601	0.6645	0.8151
No log	4.5641	178	0.6059	0.7565	0.6059	0.7784
No log	4.6154	180	0.5893	0.7614	0.5893	0.7677
No log	4.6667	182	0.6331	0.7411	0.6331	0.7956
No log	4.7179	184	0.6585	0.7279	0.6585	0.8115
No log	4.7692	186	0.6894	0.7102	0.6894	0.8303
No log	4.8205	188	0.7779	0.7099	0.7779	0.8820
No log	4.8718	190	0.7884	0.7099	0.7884	0.8879
No log	4.9231	192	0.7104	0.7166	0.7104	0.8429
No log	4.9744	194	0.6529	0.7332	0.6529	0.8080
No log	5.0256	196	0.6365	0.7379	0.6365	0.7978
No log	5.0769	198	0.6413	0.7454	0.6413	0.8008
No log	5.1282	200	0.6602	0.7337	0.6602	0.8125
No log	5.1795	202	0.7373	0.7153	0.7373	0.8587
No log	5.2308	204	0.8444	0.7075	0.8444	0.9189
No log	5.2821	206	0.8433	0.7224	0.8433	0.9183
No log	5.3333	208	0.7503	0.7288	0.7503	0.8662
No log	5.3846	210	0.6782	0.7751	0.6782	0.8235
No log	5.4359	212	0.6446	0.7671	0.6446	0.8029
No log	5.4872	214	0.6599	0.7563	0.6599	0.8123
No log	5.5385	216	0.7319	0.7229	0.7319	0.8555
No log	5.5897	218	0.7961	0.7050	0.7961	0.8922
No log	5.6410	220	0.8166	0.7014	0.8166	0.9036
No log	5.6923	222	0.8122	0.7095	0.8122	0.9012
No log	5.7436	224	0.8005	0.7092	0.8005	0.8947
No log	5.7949	226	0.7724	0.7116	0.7724	0.8789
No log	5.8462	228	0.7154	0.7493	0.7154	0.8458
No log	5.8974	230	0.6990	0.7666	0.6990	0.8360
No log	5.9487	232	0.7268	0.7608	0.7268	0.8525
No log	6.0	234	0.7916	0.6998	0.7916	0.8897
No log	6.0513	236	0.8817	0.6736	0.8817	0.9390
No log	6.1026	238	0.8925	0.6568	0.8925	0.9447
No log	6.1538	240	0.8301	0.7018	0.8301	0.9111
No log	6.2051	242	0.7195	0.7490	0.7195	0.8482
No log	6.2564	244	0.6564	0.7817	0.6564	0.8102
No log	6.3077	246	0.6537	0.7784	0.6537	0.8085
No log	6.3590	248	0.6828	0.7615	0.6828	0.8263
No log	6.4103	250	0.7492	0.7199	0.7492	0.8656
No log	6.4615	252	0.8064	0.7190	0.8064	0.8980
No log	6.5128	254	0.7885	0.7252	0.7885	0.8880
No log	6.5641	256	0.7226	0.7331	0.7226	0.8501
No log	6.6154	258	0.6653	0.7607	0.6653	0.8157
No log	6.6667	260	0.6559	0.7652	0.6559	0.8099
No log	6.7179	262	0.6533	0.7696	0.6533	0.8083
No log	6.7692	264	0.6722	0.7601	0.6722	0.8199
No log	6.8205	266	0.7000	0.7462	0.7000	0.8367
No log	6.8718	268	0.7361	0.7352	0.7361	0.8579
No log	6.9231	270	0.7745	0.7288	0.7745	0.8801
No log	6.9744	272	0.8029	0.7210	0.8029	0.8961
No log	7.0256	274	0.8552	0.6986	0.8552	0.9247
No log	7.0769	276	0.8398	0.7039	0.8398	0.9164
No log	7.1282	278	0.7690	0.7103	0.7690	0.8769
No log	7.1795	280	0.7346	0.7336	0.7346	0.8571
No log	7.2308	282	0.7332	0.7294	0.7332	0.8563
No log	7.2821	284	0.7440	0.7130	0.7440	0.8625
No log	7.3333	286	0.7685	0.7180	0.7685	0.8766
No log	7.3846	288	0.7881	0.7093	0.7881	0.8877
No log	7.4359	290	0.7708	0.7157	0.7708	0.8779
No log	7.4872	292	0.7165	0.7368	0.7165	0.8465
No log	7.5385	294	0.6626	0.7678	0.6626	0.8140
No log	7.5897	296	0.6313	0.7811	0.6313	0.7945
No log	7.6410	298	0.6297	0.7811	0.6297	0.7935
No log	7.6923	300	0.6527	0.7760	0.6527	0.8079
No log	7.7436	302	0.6773	0.7798	0.6773	0.8230
No log	7.7949	304	0.7113	0.7580	0.7113	0.8434
No log	7.8462	306	0.7456	0.7159	0.7456	0.8635
No log	7.8974	308	0.7496	0.7239	0.7496	0.8658
No log	7.9487	310	0.7433	0.7338	0.7433	0.8621
No log	8.0	312	0.7300	0.7602	0.7300	0.8544
No log	8.0513	314	0.7568	0.7218	0.7568	0.8700
No log	8.1026	316	0.7712	0.6925	0.7712	0.8782
No log	8.1538	318	0.7631	0.7086	0.7631	0.8736
No log	8.2051	320	0.7336	0.7543	0.7336	0.8565
No log	8.2564	322	0.6894	0.7703	0.6894	0.8303
No log	8.3077	324	0.6642	0.7833	0.6642	0.8150
No log	8.3590	326	0.6615	0.7833	0.6615	0.8133
No log	8.4103	328	0.6711	0.7833	0.6711	0.8192
No log	8.4615	330	0.6843	0.7754	0.6843	0.8272
No log	8.5128	332	0.6994	0.7666	0.6994	0.8363
No log	8.5641	334	0.6981	0.7540	0.6981	0.8355
No log	8.6154	336	0.6886	0.7540	0.6886	0.8298
No log	8.6667	338	0.6795	0.7506	0.6795	0.8243
No log	8.7179	340	0.6788	0.7506	0.6788	0.8239
No log	8.7692	342	0.6841	0.7461	0.6841	0.8271
No log	8.8205	344	0.6964	0.7540	0.6964	0.8345
No log	8.8718	346	0.7096	0.7287	0.7096	0.8424
No log	8.9231	348	0.7057	0.7331	0.7057	0.8400
No log	8.9744	350	0.7014	0.7395	0.7014	0.8375
No log	9.0256	352	0.6952	0.7558	0.6952	0.8338
No log	9.0769	354	0.6988	0.7558	0.6988	0.8360
No log	9.1282	356	0.7056	0.7558	0.7056	0.8400
No log	9.1795	358	0.7185	0.7415	0.7185	0.8477
No log	9.2308	360	0.7286	0.7209	0.7286	0.8536
No log	9.2821	362	0.7380	0.7225	0.7380	0.8591
No log	9.3333	364	0.7489	0.7225	0.7489	0.8654
No log	9.3846	366	0.7585	0.7225	0.7585	0.8709
No log	9.4359	368	0.7613	0.7225	0.7613	0.8726
No log	9.4872	370	0.7595	0.7225	0.7595	0.8715
No log	9.5385	372	0.7600	0.7225	0.7600	0.8718
No log	9.5897	374	0.7635	0.7225	0.7635	0.8738
No log	9.6410	376	0.7651	0.7183	0.7651	0.8747
No log	9.6923	378	0.7602	0.7225	0.7602	0.8719
No log	9.7436	380	0.7556	0.7225	0.7556	0.8693
No log	9.7949	382	0.7509	0.7225	0.7509	0.8666
No log	9.8462	384	0.7466	0.7225	0.7466	0.8641
No log	9.8974	386	0.7434	0.7225	0.7434	0.8622
No log	9.9487	388	0.7410	0.7225	0.7410	0.8608
No log	10.0	390	0.7400	0.7168	0.7400	0.8602

Framework versions

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