ArabicNewSplits8_usingALLEssays_FineTuningAraBERT_run2_AugV5_k11_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: 0.7383
• Qwk: 0.6705
• Mse: 0.7383
• Rmse: 0.8593

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: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	0.0370	2	5.1582	-0.0293	5.1582	2.2712
No log	0.0741	4	2.9451	0.0894	2.9451	1.7161
No log	0.1111	6	1.9482	0.0060	1.9482	1.3958
No log	0.1481	8	1.9357	0.0218	1.9357	1.3913
No log	0.1852	10	1.3440	0.1447	1.3440	1.1593
No log	0.2222	12	1.1297	0.1778	1.1297	1.0629
No log	0.2593	14	1.1595	0.2297	1.1595	1.0768
No log	0.2963	16	1.3113	0.1763	1.3113	1.1451
No log	0.3333	18	1.2995	0.2442	1.2995	1.1400
No log	0.3704	20	1.4186	0.0321	1.4186	1.1910
No log	0.4074	22	1.3439	0.0962	1.3439	1.1593
No log	0.4444	24	1.0845	0.2536	1.0845	1.0414
No log	0.4815	26	1.1006	0.1735	1.1006	1.0491
No log	0.5185	28	1.0681	0.2320	1.0681	1.0335
No log	0.5556	30	0.9930	0.3515	0.9930	0.9965
No log	0.5926	32	1.4522	0.1079	1.4522	1.2051
No log	0.6296	34	1.8048	0.1954	1.8048	1.3434
No log	0.6667	36	1.6305	0.1388	1.6305	1.2769
No log	0.7037	38	1.5254	0.1466	1.5254	1.2351
No log	0.7407	40	1.2470	0.2100	1.2470	1.1167
No log	0.7778	42	0.9309	0.4556	0.9309	0.9648
No log	0.8148	44	0.8458	0.4471	0.8458	0.9197
No log	0.8519	46	0.8096	0.4612	0.8096	0.8998
No log	0.8889	48	0.7829	0.5022	0.7829	0.8848
No log	0.9259	50	0.9388	0.5305	0.9388	0.9689
No log	0.9630	52	0.9791	0.5592	0.9791	0.9895
No log	1.0	54	0.7780	0.5869	0.7780	0.8820
No log	1.0370	56	0.6944	0.5382	0.6944	0.8333
No log	1.0741	58	0.7202	0.5666	0.7202	0.8486
No log	1.1111	60	0.9667	0.6095	0.9667	0.9832
No log	1.1481	62	1.3592	0.3928	1.3592	1.1659
No log	1.1852	64	1.5925	0.3539	1.5925	1.2620
No log	1.2222	66	1.2881	0.3890	1.2881	1.1349
No log	1.2593	68	0.8908	0.5306	0.8908	0.9438
No log	1.2963	70	0.8573	0.5107	0.8573	0.9259
No log	1.3333	72	0.8373	0.5107	0.8373	0.9150
No log	1.3704	74	0.8491	0.5261	0.8491	0.9215
No log	1.4074	76	1.1336	0.4468	1.1336	1.0647
No log	1.4444	78	1.2444	0.3907	1.2444	1.1155
No log	1.4815	80	0.8636	0.6269	0.8636	0.9293
No log	1.5185	82	0.6996	0.5498	0.6996	0.8364
No log	1.5556	84	0.6915	0.6136	0.6915	0.8316
No log	1.5926	86	0.7244	0.6706	0.7244	0.8511
No log	1.6296	88	0.8982	0.5693	0.8982	0.9478
No log	1.6667	90	0.8127	0.6434	0.8127	0.9015
No log	1.7037	92	0.6419	0.6835	0.6419	0.8012
No log	1.7407	94	0.7488	0.6084	0.7488	0.8653
No log	1.7778	96	0.7687	0.6047	0.7687	0.8768
No log	1.8148	98	0.6458	0.6591	0.6458	0.8036
No log	1.8519	100	0.8751	0.5915	0.8751	0.9355
No log	1.8889	102	0.7929	0.6238	0.7929	0.8904
No log	1.9259	104	0.6451	0.6558	0.6451	0.8032
No log	1.9630	106	0.6710	0.6411	0.6710	0.8192
No log	2.0	108	0.7756	0.6007	0.7756	0.8807
No log	2.0370	110	0.8270	0.5913	0.8270	0.9094
No log	2.0741	112	0.6890	0.6281	0.6890	0.8301
No log	2.1111	114	0.7053	0.6742	0.7053	0.8398
No log	2.1481	116	0.6739	0.6874	0.6739	0.8209
No log	2.1852	118	0.7663	0.6454	0.7663	0.8754
No log	2.2222	120	1.0137	0.5782	1.0137	1.0068
No log	2.2593	122	0.8670	0.6112	0.8670	0.9311
No log	2.2963	124	0.6606	0.7005	0.6606	0.8128
No log	2.3333	126	0.7477	0.6457	0.7477	0.8647
No log	2.3704	128	0.8169	0.6234	0.8169	0.9038
No log	2.4074	130	0.6845	0.6765	0.6845	0.8273
No log	2.4444	132	0.7370	0.6834	0.7370	0.8585
No log	2.4815	134	0.9545	0.6125	0.9545	0.9770
No log	2.5185	136	0.9184	0.6333	0.9184	0.9583
No log	2.5556	138	0.7377	0.6500	0.7377	0.8589
No log	2.5926	140	0.6783	0.6523	0.6783	0.8236
No log	2.6296	142	0.6913	0.6730	0.6913	0.8315
No log	2.6667	144	0.6764	0.6532	0.6764	0.8224
No log	2.7037	146	0.6679	0.6908	0.6679	0.8173
No log	2.7407	148	0.6526	0.6911	0.6526	0.8079
No log	2.7778	150	0.6882	0.6528	0.6882	0.8296
No log	2.8148	152	0.6503	0.6682	0.6503	0.8064
No log	2.8519	154	0.6898	0.6634	0.6898	0.8305
No log	2.8889	156	0.9814	0.5519	0.9814	0.9907
No log	2.9259	158	0.9708	0.5519	0.9708	0.9853
No log	2.9630	160	0.7297	0.6795	0.7297	0.8542
No log	3.0	162	0.6766	0.7063	0.6766	0.8226
No log	3.0370	164	0.6919	0.6720	0.6919	0.8318
No log	3.0741	166	0.7001	0.6317	0.7001	0.8367
No log	3.1111	168	0.7021	0.6499	0.7021	0.8379
No log	3.1481	170	0.7063	0.6490	0.7063	0.8404
No log	3.1852	172	0.7250	0.5672	0.7250	0.8514
No log	3.2222	174	0.7044	0.6467	0.7044	0.8393
No log	3.2593	176	0.6943	0.6861	0.6943	0.8332
No log	3.2963	178	0.7211	0.6775	0.7211	0.8492
No log	3.3333	180	0.6752	0.6902	0.6752	0.8217
No log	3.3704	182	0.6684	0.6447	0.6684	0.8176
No log	3.4074	184	0.6672	0.6310	0.6672	0.8168
No log	3.4444	186	0.6713	0.6905	0.6713	0.8193
No log	3.4815	188	0.7255	0.6551	0.7255	0.8518
No log	3.5185	190	0.6752	0.6800	0.6752	0.8217
No log	3.5556	192	0.6699	0.6858	0.6699	0.8185
No log	3.5926	194	0.6635	0.6751	0.6635	0.8146
No log	3.6296	196	0.6588	0.6934	0.6588	0.8117
No log	3.6667	198	0.6890	0.6557	0.6890	0.8301
No log	3.7037	200	0.6475	0.7013	0.6475	0.8047
No log	3.7407	202	0.6564	0.7312	0.6564	0.8102
No log	3.7778	204	0.8209	0.6249	0.8209	0.9061
No log	3.8148	206	0.8354	0.6301	0.8354	0.9140
No log	3.8519	208	0.7014	0.7205	0.7014	0.8375
No log	3.8889	210	0.6758	0.7159	0.6758	0.8221
No log	3.9259	212	0.7382	0.6855	0.7382	0.8592
No log	3.9630	214	0.7761	0.6530	0.7761	0.8810
No log	4.0	216	0.7448	0.6870	0.7448	0.8630
No log	4.0370	218	0.7884	0.6597	0.7884	0.8879
No log	4.0741	220	0.7433	0.6764	0.7433	0.8621
No log	4.1111	222	0.6607	0.7042	0.6607	0.8128
No log	4.1481	224	0.6650	0.7304	0.6650	0.8155
No log	4.1852	226	0.6633	0.7159	0.6633	0.8144
No log	4.2222	228	0.6680	0.6790	0.6680	0.8173
No log	4.2593	230	0.6777	0.7060	0.6777	0.8232
No log	4.2963	232	0.6772	0.6738	0.6772	0.8229
No log	4.3333	234	0.6781	0.6698	0.6781	0.8234
No log	4.3704	236	0.7097	0.6219	0.7097	0.8425
No log	4.4074	238	0.7100	0.6219	0.7100	0.8426
No log	4.4444	240	0.6937	0.6435	0.6937	0.8329
No log	4.4815	242	0.6963	0.6020	0.6963	0.8344
No log	4.5185	244	0.7205	0.5890	0.7205	0.8488
No log	4.5556	246	0.7931	0.6254	0.7931	0.8905
No log	4.5926	248	0.8377	0.6278	0.8377	0.9152
No log	4.6296	250	0.8437	0.6472	0.8437	0.9185
No log	4.6667	252	0.7878	0.6653	0.7878	0.8876
No log	4.7037	254	0.8042	0.6703	0.8042	0.8968
No log	4.7407	256	0.8785	0.6008	0.8785	0.9373
No log	4.7778	258	0.8493	0.6276	0.8493	0.9216
No log	4.8148	260	0.8790	0.5963	0.8790	0.9375
No log	4.8519	262	0.7950	0.6467	0.7950	0.8917
No log	4.8889	264	0.7834	0.6090	0.7834	0.8851
No log	4.9259	266	0.8037	0.6378	0.8037	0.8965
No log	4.9630	268	0.7598	0.6020	0.7598	0.8716
No log	5.0	270	0.7478	0.5602	0.7478	0.8647
No log	5.0370	272	0.7728	0.5126	0.7728	0.8791
No log	5.0741	274	0.7408	0.5332	0.7408	0.8607
No log	5.1111	276	0.8076	0.6142	0.8076	0.8987
No log	5.1481	278	0.9886	0.5462	0.9886	0.9943
No log	5.1852	280	0.9712	0.5639	0.9712	0.9855
No log	5.2222	282	0.7986	0.6345	0.7986	0.8936
No log	5.2593	284	0.7137	0.6539	0.7137	0.8448
No log	5.2963	286	0.7044	0.6747	0.7044	0.8393
No log	5.3333	288	0.7435	0.6682	0.7435	0.8623
No log	5.3704	290	0.8303	0.6538	0.8303	0.9112
No log	5.4074	292	0.8063	0.6325	0.8063	0.8979
No log	5.4444	294	0.7119	0.6692	0.7119	0.8438
No log	5.4815	296	0.6981	0.6141	0.6981	0.8355
No log	5.5185	298	0.7000	0.6090	0.7000	0.8366
No log	5.5556	300	0.6788	0.6658	0.6788	0.8239
No log	5.5926	302	0.6697	0.6669	0.6697	0.8183
No log	5.6296	304	0.7433	0.6635	0.7433	0.8622
No log	5.6667	306	0.9318	0.6364	0.9318	0.9653
No log	5.7037	308	0.9549	0.6233	0.9549	0.9772
No log	5.7407	310	0.7968	0.6806	0.7968	0.8927
No log	5.7778	312	0.7204	0.6870	0.7204	0.8487
No log	5.8148	314	0.7023	0.6856	0.7023	0.8381
No log	5.8519	316	0.7030	0.6872	0.7030	0.8384
No log	5.8889	318	0.7709	0.6402	0.7709	0.8780
No log	5.9259	320	0.9033	0.6129	0.9033	0.9504
No log	5.9630	322	0.8852	0.6109	0.8852	0.9409
No log	6.0	324	0.7636	0.6291	0.7636	0.8739
No log	6.0370	326	0.6921	0.6428	0.6921	0.8319
No log	6.0741	328	0.6551	0.6649	0.6551	0.8094
No log	6.1111	330	0.6466	0.6781	0.6466	0.8041
No log	6.1481	332	0.6462	0.7098	0.6462	0.8039
No log	6.1852	334	0.6342	0.7180	0.6342	0.7964
No log	6.2222	336	0.6191	0.7092	0.6191	0.7868
No log	6.2593	338	0.6026	0.7174	0.6026	0.7763
No log	6.2963	340	0.6127	0.6476	0.6127	0.7827
No log	6.3333	342	0.6247	0.6435	0.6247	0.7904
No log	6.3704	344	0.6215	0.6435	0.6215	0.7883
No log	6.4074	346	0.6229	0.6873	0.6229	0.7892
No log	6.4444	348	0.6869	0.6928	0.6869	0.8288
No log	6.4815	350	0.7440	0.6689	0.7440	0.8625
No log	6.5185	352	0.6704	0.7332	0.6704	0.8188
No log	6.5556	354	0.6319	0.7164	0.6319	0.7949
No log	6.5926	356	0.6948	0.6710	0.6948	0.8335
No log	6.6296	358	0.7795	0.6404	0.7795	0.8829
No log	6.6667	360	0.7500	0.6232	0.7500	0.8660
No log	6.7037	362	0.6727	0.6199	0.6727	0.8202
No log	6.7407	364	0.6398	0.6714	0.6398	0.7999
No log	6.7778	366	0.6334	0.6856	0.6334	0.7958
No log	6.8148	368	0.6546	0.6486	0.6546	0.8091
No log	6.8519	370	0.6926	0.6505	0.6926	0.8322
No log	6.8889	372	0.7667	0.6228	0.7667	0.8756
No log	6.9259	374	0.8597	0.6405	0.8597	0.9272
No log	6.9630	376	0.8342	0.6371	0.8342	0.9134
No log	7.0	378	0.7060	0.6549	0.7060	0.8402
No log	7.0370	380	0.6434	0.7070	0.6434	0.8021
No log	7.0741	382	0.6377	0.7066	0.6377	0.7986
No log	7.1111	384	0.6513	0.6949	0.6513	0.8070
No log	7.1481	386	0.8129	0.6486	0.8129	0.9016
No log	7.1852	388	0.9713	0.6050	0.9713	0.9856
No log	7.2222	390	0.9143	0.6183	0.9143	0.9562
No log	7.2593	392	0.7174	0.6183	0.7174	0.8470
No log	7.2963	394	0.6381	0.6262	0.6381	0.7988
No log	7.3333	396	0.6273	0.6521	0.6273	0.7920
No log	7.3704	398	0.6173	0.7116	0.6173	0.7857
No log	7.4074	400	0.6088	0.7195	0.6088	0.7803
No log	7.4444	402	0.6326	0.6839	0.6326	0.7954
No log	7.4815	404	0.7490	0.6794	0.7490	0.8654
No log	7.5185	406	0.7862	0.6639	0.7862	0.8867
No log	7.5556	408	0.7036	0.6803	0.7036	0.8388
No log	7.5926	410	0.6111	0.7346	0.6111	0.7817
No log	7.6296	412	0.6021	0.7188	0.6021	0.7760
No log	7.6667	414	0.6034	0.7159	0.6034	0.7768
No log	7.7037	416	0.6094	0.7449	0.6094	0.7806
No log	7.7407	418	0.6675	0.6840	0.6675	0.8170
No log	7.7778	420	0.6999	0.6704	0.6999	0.8366
No log	7.8148	422	0.6663	0.7184	0.6663	0.8163
No log	7.8519	424	0.6393	0.7080	0.6393	0.7996
No log	7.8889	426	0.6048	0.7221	0.6048	0.7777
No log	7.9259	428	0.6122	0.6978	0.6122	0.7824
No log	7.9630	430	0.6045	0.6786	0.6045	0.7775
No log	8.0	432	0.6372	0.6569	0.6372	0.7982
No log	8.0370	434	0.6645	0.6583	0.6645	0.8151
No log	8.0741	436	0.6414	0.6754	0.6414	0.8009
No log	8.1111	438	0.6132	0.7226	0.6132	0.7831
No log	8.1481	440	0.6436	0.6428	0.6436	0.8023
No log	8.1852	442	0.6694	0.6571	0.6694	0.8182
No log	8.2222	444	0.6295	0.6960	0.6295	0.7934
No log	8.2593	446	0.6222	0.7205	0.6222	0.7888
No log	8.2963	448	0.7349	0.6646	0.7349	0.8572
No log	8.3333	450	0.7447	0.6565	0.7447	0.8630
No log	8.3704	452	0.6676	0.6732	0.6676	0.8171
No log	8.4074	454	0.6152	0.7441	0.6152	0.7844
No log	8.4444	456	0.6365	0.7001	0.6365	0.7978
No log	8.4815	458	0.6284	0.6901	0.6284	0.7927
No log	8.5185	460	0.6230	0.7090	0.6230	0.7893
No log	8.5556	462	0.6746	0.6635	0.6746	0.8213
No log	8.5926	464	0.7545	0.6447	0.7545	0.8686
No log	8.6296	466	0.7223	0.6520	0.7223	0.8499
No log	8.6667	468	0.6425	0.6790	0.6425	0.8015
No log	8.7037	470	0.6427	0.6936	0.6427	0.8017
No log	8.7407	472	0.6380	0.6917	0.6380	0.7988
No log	8.7778	474	0.6209	0.7002	0.6209	0.7879
No log	8.8148	476	0.6189	0.7124	0.6189	0.7867
No log	8.8519	478	0.6267	0.7121	0.6267	0.7916
No log	8.8889	480	0.6397	0.7178	0.6397	0.7998
No log	8.9259	482	0.7002	0.6862	0.7002	0.8368
No log	8.9630	484	0.6574	0.7010	0.6574	0.8108
No log	9.0	486	0.6104	0.7409	0.6104	0.7813
No log	9.0370	488	0.5756	0.7491	0.5756	0.7587
No log	9.0741	490	0.5769	0.7292	0.5769	0.7596
No log	9.1111	492	0.5713	0.7147	0.5713	0.7558
No log	9.1481	494	0.5938	0.6549	0.5938	0.7706
No log	9.1852	496	0.6369	0.6907	0.6369	0.7981
No log	9.2222	498	0.6173	0.6415	0.6173	0.7857
0.3915	9.2593	500	0.5858	0.6725	0.5858	0.7654
0.3915	9.2963	502	0.6419	0.6571	0.6419	0.8012
0.3915	9.3333	504	0.8153	0.6480	0.8153	0.9030
0.3915	9.3704	506	0.8965	0.6224	0.8965	0.9468
0.3915	9.4074	508	0.8564	0.6285	0.8564	0.9254
0.3915	9.4444	510	0.7383	0.6705	0.7383	0.8593

Framework versions

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