ArabicNewSplits8_usingALLEssays_FineTuningAraBERT_run3_AugV5_k8_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: 0.6223
• Qwk: 0.6745
• Mse: 0.6223
• Rmse: 0.7888

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	0.0488	2	5.1638	0.0065	5.1638	2.2724
No log	0.0976	4	3.1961	0.0935	3.1961	1.7878
No log	0.1463	6	2.2704	-0.0074	2.2704	1.5068
No log	0.1951	8	1.5706	0.0880	1.5706	1.2532
No log	0.2439	10	1.1270	0.3598	1.1270	1.0616
No log	0.2927	12	1.1983	0.3991	1.1983	1.0947
No log	0.3415	14	1.2467	0.3655	1.2467	1.1166
No log	0.3902	16	1.1561	0.2996	1.1561	1.0752
No log	0.4390	18	1.1101	0.3432	1.1101	1.0536
No log	0.4878	20	1.0886	0.3970	1.0886	1.0434
No log	0.5366	22	1.2042	0.3525	1.2042	1.0974
No log	0.5854	24	1.3838	0.2224	1.3838	1.1763
No log	0.6341	26	1.1412	0.3896	1.1412	1.0683
No log	0.6829	28	0.9157	0.4728	0.9157	0.9569
No log	0.7317	30	0.8852	0.4810	0.8852	0.9408
No log	0.7805	32	0.7947	0.4918	0.7947	0.8914
No log	0.8293	34	0.7262	0.6033	0.7262	0.8521
No log	0.8780	36	0.7570	0.5776	0.7570	0.8700
No log	0.9268	38	0.7579	0.6184	0.7579	0.8706
No log	0.9756	40	0.6644	0.6713	0.6644	0.8151
No log	1.0244	42	0.6632	0.6280	0.6632	0.8144
No log	1.0732	44	0.7050	0.6776	0.7050	0.8396
No log	1.1220	46	0.9084	0.6232	0.9084	0.9531
No log	1.1707	48	0.8858	0.6632	0.8858	0.9412
No log	1.2195	50	0.7324	0.6959	0.7324	0.8558
No log	1.2683	52	0.6954	0.6702	0.6954	0.8339
No log	1.3171	54	0.6973	0.6542	0.6973	0.8351
No log	1.3659	56	0.8621	0.6631	0.8621	0.9285
No log	1.4146	58	0.7286	0.6610	0.7286	0.8536
No log	1.4634	60	0.6146	0.6619	0.6146	0.7840
No log	1.5122	62	0.6614	0.6410	0.6614	0.8133
No log	1.5610	64	0.6112	0.6684	0.6112	0.7818
No log	1.6098	66	0.5986	0.6693	0.5986	0.7737
No log	1.6585	68	0.5967	0.7009	0.5967	0.7725
No log	1.7073	70	0.6068	0.6944	0.6068	0.7790
No log	1.7561	72	0.7712	0.6889	0.7712	0.8782
No log	1.8049	74	1.0404	0.5391	1.0404	1.0200
No log	1.8537	76	0.8123	0.6425	0.8123	0.9013
No log	1.9024	78	0.6766	0.6961	0.6766	0.8226
No log	1.9512	80	0.6655	0.6793	0.6655	0.8158
No log	2.0	82	0.7233	0.6033	0.7233	0.8505
No log	2.0488	84	0.7514	0.5648	0.7514	0.8668
No log	2.0976	86	0.8011	0.5768	0.8011	0.8951
No log	2.1463	88	0.7632	0.5753	0.7632	0.8736
No log	2.1951	90	0.6692	0.6309	0.6692	0.8181
No log	2.2439	92	0.6478	0.6791	0.6478	0.8048
No log	2.2927	94	0.6461	0.6945	0.6461	0.8038
No log	2.3415	96	0.7950	0.6622	0.7950	0.8916
No log	2.3902	98	0.9959	0.5773	0.9959	0.9979
No log	2.4390	100	0.8835	0.6179	0.8835	0.9400
No log	2.4878	102	0.6952	0.7239	0.6952	0.8338
No log	2.5366	104	0.7638	0.7145	0.7638	0.8740
No log	2.5854	106	0.7659	0.7248	0.7659	0.8751
No log	2.6341	108	0.7202	0.7143	0.7202	0.8487
No log	2.6829	110	0.7174	0.7107	0.7174	0.8470
No log	2.7317	112	0.7107	0.7064	0.7107	0.8430
No log	2.7805	114	0.7119	0.7124	0.7119	0.8438
No log	2.8293	116	0.7476	0.6936	0.7476	0.8646
No log	2.8780	118	0.7564	0.6773	0.7564	0.8697
No log	2.9268	120	0.7297	0.6823	0.7297	0.8542
No log	2.9756	122	0.7082	0.6795	0.7082	0.8416
No log	3.0244	124	0.6871	0.6656	0.6871	0.8289
No log	3.0732	126	0.6738	0.6797	0.6738	0.8209
No log	3.1220	128	0.6707	0.6982	0.6707	0.8190
No log	3.1707	130	0.7216	0.6806	0.7216	0.8495
No log	3.2195	132	0.7590	0.6603	0.7590	0.8712
No log	3.2683	134	0.7103	0.7302	0.7103	0.8428
No log	3.3171	136	0.7401	0.7267	0.7401	0.8603
No log	3.3659	138	0.7449	0.7231	0.7449	0.8631
No log	3.4146	140	0.7288	0.7151	0.7288	0.8537
No log	3.4634	142	0.7899	0.6603	0.7899	0.8888
No log	3.5122	144	0.7488	0.6835	0.7488	0.8653
No log	3.5610	146	0.6854	0.7247	0.6854	0.8279
No log	3.6098	148	0.6846	0.7071	0.6846	0.8274
No log	3.6585	150	0.6832	0.7067	0.6832	0.8265
No log	3.7073	152	0.7073	0.7060	0.7073	0.8410
No log	3.7561	154	0.7119	0.7189	0.7119	0.8437
No log	3.8049	156	0.7728	0.6683	0.7728	0.8791
No log	3.8537	158	0.8876	0.6225	0.8876	0.9421
No log	3.9024	160	0.7960	0.6757	0.7960	0.8922
No log	3.9512	162	0.7313	0.6897	0.7313	0.8552
No log	4.0	164	0.7957	0.6676	0.7957	0.8920
No log	4.0488	166	0.7127	0.6592	0.7127	0.8442
No log	4.0976	168	0.7741	0.6291	0.7741	0.8799
No log	4.1463	170	0.9071	0.5945	0.9071	0.9524
No log	4.1951	172	0.7743	0.6439	0.7743	0.8799
No log	4.2439	174	0.7568	0.6672	0.7568	0.8699
No log	4.2927	176	0.7668	0.6586	0.7668	0.8757
No log	4.3415	178	0.6982	0.6646	0.6982	0.8356
No log	4.3902	180	0.6770	0.7337	0.6770	0.8228
No log	4.4390	182	0.7230	0.7270	0.7230	0.8503
No log	4.4878	184	0.8826	0.6641	0.8826	0.9395
No log	4.5366	186	0.8786	0.6784	0.8786	0.9374
No log	4.5854	188	0.7021	0.7152	0.7021	0.8379
No log	4.6341	190	0.6901	0.6835	0.6901	0.8307
No log	4.6829	192	0.6816	0.6824	0.6816	0.8256
No log	4.7317	194	0.7501	0.7090	0.7501	0.8661
No log	4.7805	196	0.8010	0.6619	0.8010	0.8950
No log	4.8293	198	0.7436	0.7323	0.7436	0.8623
No log	4.8780	200	0.7084	0.6883	0.7084	0.8416
No log	4.9268	202	0.7517	0.6866	0.7517	0.8670
No log	4.9756	204	0.7618	0.6807	0.7618	0.8728
No log	5.0244	206	0.7490	0.6991	0.7490	0.8655
No log	5.0732	208	0.6851	0.6960	0.6851	0.8277
No log	5.1220	210	0.6804	0.6971	0.6805	0.8249
No log	5.1707	212	0.6491	0.6668	0.6491	0.8056
No log	5.2195	214	0.7845	0.6170	0.7845	0.8857
No log	5.2683	216	1.0609	0.5793	1.0609	1.0300
No log	5.3171	218	0.9794	0.5997	0.9794	0.9896
No log	5.3659	220	0.7332	0.6601	0.7332	0.8563
No log	5.4146	222	0.6233	0.7013	0.6233	0.7895
No log	5.4634	224	0.7296	0.6627	0.7296	0.8542
No log	5.5122	226	0.6673	0.6953	0.6673	0.8169
No log	5.5610	228	0.6583	0.7006	0.6583	0.8114
No log	5.6098	230	1.0197	0.5691	1.0197	1.0098
No log	5.6585	232	1.0712	0.5458	1.0712	1.0350
No log	5.7073	234	0.8085	0.6199	0.8085	0.8992
No log	5.7561	236	0.6305	0.6935	0.6305	0.7940
No log	5.8049	238	0.7589	0.6125	0.7589	0.8711
No log	5.8537	240	0.7784	0.6005	0.7784	0.8823
No log	5.9024	242	0.7103	0.6159	0.7103	0.8428
No log	5.9512	244	0.6396	0.6704	0.6396	0.7998
No log	6.0	246	0.6325	0.6824	0.6325	0.7953
No log	6.0488	248	0.6409	0.6798	0.6409	0.8006
No log	6.0976	250	0.6555	0.7142	0.6555	0.8096
No log	6.1463	252	0.7036	0.6992	0.7036	0.8388
No log	6.1951	254	0.8301	0.6485	0.8301	0.9111
No log	6.2439	256	0.8336	0.6538	0.8336	0.9130
No log	6.2927	258	0.7206	0.7109	0.7206	0.8489
No log	6.3415	260	0.6684	0.6993	0.6684	0.8176
No log	6.3902	262	0.6553	0.6993	0.6553	0.8095
No log	6.4390	264	0.6964	0.6909	0.6964	0.8345
No log	6.4878	266	0.7642	0.6348	0.7642	0.8742
No log	6.5366	268	0.6694	0.6857	0.6694	0.8182
No log	6.5854	270	0.6447	0.6987	0.6447	0.8029
No log	6.6341	272	0.6660	0.7026	0.6660	0.8161
No log	6.6829	274	0.6674	0.7020	0.6674	0.8169
No log	6.7317	276	0.6756	0.6983	0.6756	0.8220
No log	6.7805	278	0.7291	0.6790	0.7291	0.8539
No log	6.8293	280	0.7519	0.6675	0.7519	0.8671
No log	6.8780	282	0.8204	0.6629	0.8204	0.9058
No log	6.9268	284	0.7373	0.6618	0.7373	0.8587
No log	6.9756	286	0.6874	0.6630	0.6874	0.8291
No log	7.0244	288	0.7000	0.6391	0.7000	0.8367
No log	7.0732	290	0.6927	0.6003	0.6927	0.8323
No log	7.1220	292	0.6910	0.6495	0.6910	0.8312
No log	7.1707	294	0.7025	0.6377	0.7025	0.8382
No log	7.2195	296	0.6895	0.6477	0.6895	0.8304
No log	7.2683	298	0.6563	0.6684	0.6563	0.8101
No log	7.3171	300	0.6277	0.6806	0.6277	0.7923
No log	7.3659	302	0.6357	0.6767	0.6357	0.7973
No log	7.4146	304	0.6422	0.6654	0.6422	0.8014
No log	7.4634	306	0.6182	0.7092	0.6182	0.7863
No log	7.5122	308	0.6193	0.7130	0.6193	0.7870
No log	7.5610	310	0.6309	0.7121	0.6309	0.7943
No log	7.6098	312	0.7229	0.6898	0.7229	0.8502
No log	7.6585	314	0.7746	0.6667	0.7746	0.8801
No log	7.7073	316	0.7459	0.6867	0.7459	0.8636
No log	7.7561	318	0.7551	0.6777	0.7551	0.8690
No log	7.8049	320	0.6395	0.6672	0.6395	0.7997
No log	7.8537	322	0.6282	0.6969	0.6282	0.7926
No log	7.9024	324	0.6614	0.6684	0.6614	0.8133
No log	7.9512	326	0.6802	0.6743	0.6802	0.8247
No log	8.0	328	0.6672	0.6891	0.6672	0.8168
No log	8.0488	330	0.7235	0.6796	0.7235	0.8506
No log	8.0976	332	0.8975	0.6666	0.8975	0.9474
No log	8.1463	334	1.1803	0.5542	1.1803	1.0864
No log	8.1951	336	1.2042	0.5310	1.2042	1.0974
No log	8.2439	338	1.0004	0.6206	1.0004	1.0002
No log	8.2927	340	0.7465	0.6849	0.7465	0.8640
No log	8.3415	342	0.6837	0.7317	0.6837	0.8268
No log	8.3902	344	0.7335	0.7050	0.7335	0.8564
No log	8.4390	346	0.6788	0.7279	0.6788	0.8239
No log	8.4878	348	0.6481	0.6820	0.6481	0.8051
No log	8.5366	350	0.7520	0.6732	0.7520	0.8672
No log	8.5854	352	0.7684	0.6723	0.7684	0.8766
No log	8.6341	354	0.6854	0.7006	0.6854	0.8279
No log	8.6829	356	0.6411	0.7083	0.6411	0.8007
No log	8.7317	358	0.6612	0.6855	0.6612	0.8131
No log	8.7805	360	0.6394	0.7003	0.6394	0.7996
No log	8.8293	362	0.6506	0.6992	0.6506	0.8066
No log	8.8780	364	0.6648	0.6685	0.6648	0.8153
No log	8.9268	366	0.6499	0.6923	0.6499	0.8062
No log	8.9756	368	0.6297	0.6576	0.6297	0.7935
No log	9.0244	370	0.6246	0.6847	0.6246	0.7903
No log	9.0732	372	0.6341	0.7079	0.6341	0.7963
No log	9.1220	374	0.6486	0.6929	0.6486	0.8054
No log	9.1707	376	0.6623	0.6873	0.6623	0.8138
No log	9.2195	378	0.7237	0.6675	0.7237	0.8507
No log	9.2683	380	0.7839	0.6567	0.7839	0.8854
No log	9.3171	382	0.7350	0.6645	0.7350	0.8573
No log	9.3659	384	0.7231	0.6473	0.7231	0.8503
No log	9.4146	386	0.7321	0.6343	0.7321	0.8557
No log	9.4634	388	0.8042	0.6440	0.8042	0.8968
No log	9.5122	390	0.7974	0.6414	0.7974	0.8930
No log	9.5610	392	0.7371	0.6724	0.7371	0.8585
No log	9.6098	394	0.7564	0.6724	0.7564	0.8697
No log	9.6585	396	0.6931	0.6754	0.6931	0.8326
No log	9.7073	398	0.6445	0.7087	0.6445	0.8028
No log	9.7561	400	0.6464	0.7061	0.6464	0.8040
No log	9.8049	402	0.6460	0.6955	0.6460	0.8038
No log	9.8537	404	0.6337	0.6989	0.6337	0.7961
No log	9.9024	406	0.6614	0.6805	0.6614	0.8133
No log	9.9512	408	0.7079	0.6256	0.7079	0.8414
No log	10.0	410	0.7237	0.6256	0.7237	0.8507
No log	10.0488	412	0.7063	0.6206	0.7063	0.8404
No log	10.0976	414	0.6273	0.7093	0.6273	0.7920
No log	10.1463	416	0.6526	0.6864	0.6526	0.8078
No log	10.1951	418	0.6785	0.6894	0.6785	0.8237
No log	10.2439	420	0.6781	0.6616	0.6781	0.8235
No log	10.2927	422	0.6142	0.7171	0.6142	0.7837
No log	10.3415	424	0.6368	0.6887	0.6368	0.7980
No log	10.3902	426	0.6330	0.6775	0.6330	0.7956
No log	10.4390	428	0.6107	0.7122	0.6107	0.7815
No log	10.4878	430	0.6777	0.6439	0.6777	0.8232
No log	10.5366	432	0.7912	0.6216	0.7912	0.8895
No log	10.5854	434	0.7696	0.6439	0.7696	0.8773
No log	10.6341	436	0.6640	0.6732	0.6640	0.8148
No log	10.6829	438	0.6491	0.7409	0.6491	0.8057
No log	10.7317	440	0.6736	0.7310	0.6736	0.8207
No log	10.7805	442	0.6771	0.7043	0.6771	0.8229
No log	10.8293	444	0.7512	0.6864	0.7512	0.8667
No log	10.8780	446	0.8845	0.6374	0.8845	0.9405
No log	10.9268	448	0.9241	0.6278	0.9241	0.9613
No log	10.9756	450	0.8002	0.6207	0.8002	0.8945
No log	11.0244	452	0.6740	0.6768	0.6740	0.8210
No log	11.0732	454	0.6203	0.6767	0.6203	0.7876
No log	11.1220	456	0.6140	0.7182	0.6140	0.7836
No log	11.1707	458	0.6763	0.6665	0.6763	0.8224
No log	11.2195	460	0.8130	0.6631	0.8130	0.9016
No log	11.2683	462	0.8206	0.6631	0.8206	0.9059
No log	11.3171	464	0.7542	0.6675	0.7542	0.8684
No log	11.3659	466	0.7664	0.6598	0.7664	0.8754
No log	11.4146	468	0.7829	0.6358	0.7829	0.8848
No log	11.4634	470	0.8032	0.6358	0.8032	0.8962
No log	11.5122	472	0.7869	0.6358	0.7869	0.8871
No log	11.5610	474	0.6841	0.7010	0.6841	0.8271
No log	11.6098	476	0.6425	0.7246	0.6425	0.8016
No log	11.6585	478	0.6396	0.7314	0.6396	0.7998
No log	11.7073	480	0.6974	0.6985	0.6974	0.8351
No log	11.7561	482	0.7547	0.6806	0.7547	0.8687
No log	11.8049	484	0.6764	0.7325	0.6764	0.8225
No log	11.8537	486	0.6289	0.7307	0.6289	0.7930
No log	11.9024	488	0.6128	0.7205	0.6128	0.7828
No log	11.9512	490	0.6283	0.6947	0.6283	0.7927
No log	12.0	492	0.6300	0.7166	0.6300	0.7937
No log	12.0488	494	0.6278	0.7207	0.6278	0.7924
No log	12.0976	496	0.6591	0.7179	0.6591	0.8119
No log	12.1463	498	0.6631	0.7261	0.6631	0.8143
0.3633	12.1951	500	0.6577	0.7225	0.6577	0.8110
0.3633	12.2439	502	0.6568	0.7318	0.6568	0.8104
0.3633	12.2927	504	0.6365	0.7282	0.6365	0.7978
0.3633	12.3415	506	0.6395	0.7178	0.6395	0.7997
0.3633	12.3902	508	0.7053	0.6790	0.7053	0.8398
0.3633	12.4390	510	0.7055	0.7105	0.7055	0.8400
0.3633	12.4878	512	0.6466	0.6827	0.6466	0.8041
0.3633	12.5366	514	0.6270	0.7228	0.6270	0.7918
0.3633	12.5854	516	0.6342	0.7223	0.6342	0.7964
0.3633	12.6341	518	0.6399	0.7253	0.6399	0.8000
0.3633	12.6829	520	0.6409	0.7105	0.6409	0.8005
0.3633	12.7317	522	0.6728	0.6777	0.6728	0.8202
0.3633	12.7805	524	0.6619	0.6852	0.6619	0.8136
0.3633	12.8293	526	0.6476	0.6674	0.6476	0.8047
0.3633	12.8780	528	0.6223	0.6745	0.6223	0.7888

Framework versions

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