ArabicNewSplits6_FineTuningAraBERTFreeze_run3_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: 0.8759
• Qwk: 0.6521
• Mse: 0.8759
• Rmse: 0.9359

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: 16
• eval_batch_size: 16
• 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	0.1176	2	7.8171	-0.0404	7.8171	2.7959
No log	0.2353	4	5.5783	-0.0349	5.5783	2.3618
No log	0.3529	6	3.9680	0.0249	3.9680	1.9920
No log	0.4706	8	2.9350	0.0896	2.9350	1.7132
No log	0.5882	10	2.1724	0.1482	2.1724	1.4739
No log	0.7059	12	1.7123	0.1708	1.7123	1.3086
No log	0.8235	14	1.4210	0.2660	1.4210	1.1920
No log	0.9412	16	1.2598	0.1957	1.2598	1.1224
No log	1.0588	18	1.2942	0.1468	1.2942	1.1376
No log	1.1765	20	1.2683	0.1353	1.2683	1.1262
No log	1.2941	22	1.2502	0.1726	1.2502	1.1181
No log	1.4118	24	1.1792	0.2572	1.1792	1.0859
No log	1.5294	26	1.0569	0.3584	1.0569	1.0281
No log	1.6471	28	1.0019	0.3978	1.0019	1.0010
No log	1.7647	30	1.0573	0.4188	1.0573	1.0282
No log	1.8824	32	1.0881	0.3802	1.0881	1.0431
No log	2.0	34	1.0541	0.3802	1.0541	1.0267
No log	2.1176	36	0.9999	0.4188	0.9999	0.9999
No log	2.2353	38	0.9441	0.4002	0.9441	0.9717
No log	2.3529	40	0.9155	0.4065	0.9155	0.9568
No log	2.4706	42	0.9060	0.4263	0.9060	0.9518
No log	2.5882	44	0.8884	0.4263	0.8884	0.9425
No log	2.7059	46	0.8604	0.4465	0.8604	0.9276
No log	2.8235	48	0.8420	0.4982	0.8420	0.9176
No log	2.9412	50	0.8186	0.5024	0.8186	0.9048
No log	3.0588	52	0.8155	0.5166	0.8155	0.9031
No log	3.1765	54	0.8321	0.5057	0.8321	0.9122
No log	3.2941	56	0.8509	0.5023	0.8509	0.9224
No log	3.4118	58	0.8418	0.5219	0.8418	0.9175
No log	3.5294	60	0.8350	0.5423	0.8350	0.9138
No log	3.6471	62	0.8346	0.5252	0.8346	0.9136
No log	3.7647	64	0.8290	0.5257	0.8290	0.9105
No log	3.8824	66	0.8191	0.5123	0.8191	0.9050
No log	4.0	68	0.7900	0.5176	0.7900	0.8888
No log	4.1176	70	0.7755	0.6427	0.7755	0.8806
No log	4.2353	72	0.7708	0.6301	0.7708	0.8780
No log	4.3529	74	0.7998	0.6066	0.7998	0.8943
No log	4.4706	76	0.7688	0.6185	0.7688	0.8768
No log	4.5882	78	0.7182	0.6033	0.7182	0.8475
No log	4.7059	80	0.7008	0.6059	0.7008	0.8371
No log	4.8235	82	0.7215	0.5851	0.7215	0.8494
No log	4.9412	84	0.7233	0.5941	0.7233	0.8505
No log	5.0588	86	0.7303	0.5660	0.7303	0.8546
No log	5.1765	88	0.7249	0.5554	0.7249	0.8514
No log	5.2941	90	0.7444	0.6215	0.7444	0.8628
No log	5.4118	92	0.7665	0.6246	0.7665	0.8755
No log	5.5294	94	0.7420	0.6299	0.7420	0.8614
No log	5.6471	96	0.7241	0.6212	0.7241	0.8509
No log	5.7647	98	0.7051	0.6069	0.7051	0.8397
No log	5.8824	100	0.7412	0.5558	0.7412	0.8610
No log	6.0	102	0.7144	0.5829	0.7144	0.8452
No log	6.1176	104	0.6680	0.6678	0.6680	0.8173
No log	6.2353	106	0.6604	0.6428	0.6604	0.8127
No log	6.3529	108	0.6959	0.6257	0.6959	0.8342
No log	6.4706	110	0.7044	0.6572	0.7044	0.8393
No log	6.5882	112	0.6738	0.6395	0.6738	0.8209
No log	6.7059	114	0.6760	0.6386	0.6760	0.8222
No log	6.8235	116	0.6562	0.6735	0.6562	0.8101
No log	6.9412	118	0.6601	0.6438	0.6601	0.8125
No log	7.0588	120	0.6723	0.6820	0.6723	0.8200
No log	7.1765	122	0.7091	0.6652	0.7091	0.8421
No log	7.2941	124	0.7740	0.6472	0.7740	0.8798
No log	7.4118	126	0.7620	0.6494	0.7620	0.8729
No log	7.5294	128	0.7122	0.6663	0.7122	0.8439
No log	7.6471	130	0.7000	0.6629	0.7000	0.8367
No log	7.7647	132	0.6970	0.6381	0.6970	0.8349
No log	7.8824	134	0.6914	0.6258	0.6914	0.8315
No log	8.0	136	0.6866	0.6693	0.6866	0.8286
No log	8.1176	138	0.6817	0.6879	0.6817	0.8257
No log	8.2353	140	0.6685	0.6942	0.6685	0.8176
No log	8.3529	142	0.6456	0.6934	0.6456	0.8035
No log	8.4706	144	0.6322	0.7058	0.6322	0.7951
No log	8.5882	146	0.6382	0.6586	0.6382	0.7988
No log	8.7059	148	0.6407	0.6861	0.6407	0.8004
No log	8.8235	150	0.6394	0.6898	0.6394	0.7996
No log	8.9412	152	0.6496	0.6955	0.6496	0.8060
No log	9.0588	154	0.6766	0.6858	0.6766	0.8226
No log	9.1765	156	0.6592	0.6912	0.6592	0.8119
No log	9.2941	158	0.6518	0.6617	0.6518	0.8073
No log	9.4118	160	0.7155	0.6213	0.7155	0.8459
No log	9.5294	162	0.7445	0.5687	0.7445	0.8629
No log	9.6471	164	0.7139	0.5895	0.7139	0.8449
No log	9.7647	166	0.6695	0.6592	0.6695	0.8182
No log	9.8824	168	0.6657	0.6773	0.6657	0.8159
No log	10.0	170	0.7193	0.6816	0.7193	0.8481
No log	10.1176	172	0.7232	0.6706	0.7232	0.8504
No log	10.2353	174	0.6726	0.6668	0.6726	0.8201
No log	10.3529	176	0.6458	0.6848	0.6458	0.8036
No log	10.4706	178	0.6560	0.6746	0.6560	0.8099
No log	10.5882	180	0.6828	0.6990	0.6828	0.8263
No log	10.7059	182	0.6862	0.6847	0.6862	0.8283
No log	10.8235	184	0.7147	0.7125	0.7147	0.8454
No log	10.9412	186	0.6962	0.7238	0.6962	0.8344
No log	11.0588	188	0.6561	0.7045	0.6561	0.8100
No log	11.1765	190	0.6468	0.7022	0.6468	0.8043
No log	11.2941	192	0.6455	0.7028	0.6455	0.8034
No log	11.4118	194	0.6415	0.6883	0.6415	0.8009
No log	11.5294	196	0.6570	0.7057	0.6570	0.8106
No log	11.6471	198	0.7170	0.6206	0.7170	0.8468
No log	11.7647	200	0.7277	0.6375	0.7277	0.8531
No log	11.8824	202	0.6970	0.6697	0.6970	0.8349
No log	12.0	204	0.6652	0.6842	0.6652	0.8156
No log	12.1176	206	0.6649	0.6771	0.6649	0.8154
No log	12.2353	208	0.6753	0.6881	0.6753	0.8218
No log	12.3529	210	0.6701	0.6881	0.6701	0.8186
No log	12.4706	212	0.6569	0.6856	0.6569	0.8105
No log	12.5882	214	0.6657	0.6987	0.6657	0.8159
No log	12.7059	216	0.7084	0.6451	0.7084	0.8416
No log	12.8235	218	0.7042	0.6498	0.7042	0.8392
No log	12.9412	220	0.6672	0.6980	0.6672	0.8169
No log	13.0588	222	0.6682	0.6928	0.6682	0.8174
No log	13.1765	224	0.6759	0.6928	0.6759	0.8221
No log	13.2941	226	0.7101	0.6831	0.7101	0.8427
No log	13.4118	228	0.7439	0.6728	0.7439	0.8625
No log	13.5294	230	0.7496	0.6382	0.7496	0.8658
No log	13.6471	232	0.7037	0.6491	0.7037	0.8389
No log	13.7647	234	0.6608	0.7071	0.6608	0.8129
No log	13.8824	236	0.6832	0.6610	0.6832	0.8265
No log	14.0	238	0.7109	0.6560	0.7109	0.8431
No log	14.1176	240	0.6931	0.6580	0.6931	0.8325
No log	14.2353	242	0.6680	0.6984	0.6680	0.8173
No log	14.3529	244	0.7034	0.6561	0.7034	0.8387
No log	14.4706	246	0.7459	0.6215	0.7459	0.8636
No log	14.5882	248	0.7792	0.6206	0.7792	0.8827
No log	14.7059	250	0.7579	0.6400	0.7579	0.8706
No log	14.8235	252	0.7328	0.6864	0.7328	0.8560
No log	14.9412	254	0.7226	0.6966	0.7226	0.8500
No log	15.0588	256	0.7238	0.6988	0.7238	0.8508
No log	15.1765	258	0.7282	0.6850	0.7282	0.8534
No log	15.2941	260	0.7367	0.6805	0.7367	0.8583
No log	15.4118	262	0.7284	0.6305	0.7284	0.8534
No log	15.5294	264	0.7432	0.6177	0.7432	0.8621
No log	15.6471	266	0.7653	0.5979	0.7653	0.8748
No log	15.7647	268	0.7606	0.6042	0.7606	0.8721
No log	15.8824	270	0.7874	0.6304	0.7874	0.8874
No log	16.0	272	0.7890	0.6638	0.7890	0.8882
No log	16.1176	274	0.8058	0.6608	0.8058	0.8977
No log	16.2353	276	0.7938	0.6659	0.7938	0.8909
No log	16.3529	278	0.7808	0.6540	0.7808	0.8836
No log	16.4706	280	0.7801	0.6505	0.7801	0.8832
No log	16.5882	282	0.7956	0.6611	0.7956	0.8920
No log	16.7059	284	0.7773	0.6575	0.7773	0.8816
No log	16.8235	286	0.7574	0.6688	0.7574	0.8703
No log	16.9412	288	0.7507	0.6559	0.7507	0.8664
No log	17.0588	290	0.7626	0.6448	0.7626	0.8732
No log	17.1765	292	0.7530	0.6381	0.7530	0.8677
No log	17.2941	294	0.7645	0.6624	0.7645	0.8744
No log	17.4118	296	0.7715	0.6624	0.7715	0.8784
No log	17.5294	298	0.7880	0.6638	0.7880	0.8877
No log	17.6471	300	0.7739	0.6575	0.7739	0.8797
No log	17.7647	302	0.7741	0.6566	0.7741	0.8798
No log	17.8824	304	0.8158	0.6674	0.8158	0.9032
No log	18.0	306	0.8567	0.6449	0.8567	0.9256
No log	18.1176	308	0.8511	0.5926	0.8511	0.9226
No log	18.2353	310	0.8268	0.5888	0.8268	0.9093
No log	18.3529	312	0.7563	0.6183	0.7563	0.8697
No log	18.4706	314	0.7259	0.6742	0.7259	0.8520
No log	18.5882	316	0.7299	0.6742	0.7299	0.8544
No log	18.7059	318	0.7489	0.6684	0.7489	0.8654
No log	18.8235	320	0.7949	0.6221	0.7949	0.8916
No log	18.9412	322	0.8573	0.6083	0.8573	0.9259
No log	19.0588	324	0.8438	0.5891	0.8438	0.9186
No log	19.1765	326	0.7731	0.6641	0.7731	0.8792
No log	19.2941	328	0.7576	0.6887	0.7576	0.8704
No log	19.4118	330	0.7459	0.6887	0.7459	0.8637
No log	19.5294	332	0.7523	0.6887	0.7523	0.8673
No log	19.6471	334	0.7743	0.6304	0.7743	0.8800
No log	19.7647	336	0.8317	0.5589	0.8317	0.9120
No log	19.8824	338	0.8530	0.5884	0.8530	0.9236
No log	20.0	340	0.8523	0.6258	0.8523	0.9232
No log	20.1176	342	0.8053	0.6456	0.8053	0.8974
No log	20.2353	344	0.7481	0.6702	0.7481	0.8649
No log	20.3529	346	0.7332	0.6872	0.7332	0.8563
No log	20.4706	348	0.7456	0.6763	0.7456	0.8635
No log	20.5882	350	0.8262	0.6512	0.8262	0.9090
No log	20.7059	352	0.9659	0.6047	0.9659	0.9828
No log	20.8235	354	1.0073	0.5679	1.0073	1.0037
No log	20.9412	356	0.9560	0.5972	0.9560	0.9777
No log	21.0588	358	0.9104	0.5984	0.9104	0.9542
No log	21.1765	360	0.8469	0.6120	0.8469	0.9203
No log	21.2941	362	0.7786	0.6648	0.7786	0.8824
No log	21.4118	364	0.7355	0.6782	0.7355	0.8576
No log	21.5294	366	0.7331	0.6782	0.7331	0.8562
No log	21.6471	368	0.7482	0.6542	0.7482	0.8650
No log	21.7647	370	0.7911	0.6459	0.7911	0.8894
No log	21.8824	372	0.8053	0.6467	0.8053	0.8974
No log	22.0	374	0.8198	0.6475	0.8198	0.9054
No log	22.1176	376	0.8302	0.6569	0.8302	0.9111
No log	22.2353	378	0.8398	0.6512	0.8398	0.9164
No log	22.3529	380	0.8791	0.6603	0.8791	0.9376
No log	22.4706	382	0.8447	0.6497	0.8447	0.9191
No log	22.5882	384	0.8291	0.6582	0.8291	0.9105
No log	22.7059	386	0.8645	0.6441	0.8645	0.9298
No log	22.8235	388	0.8570	0.6398	0.8570	0.9258
No log	22.9412	390	0.8285	0.6430	0.8285	0.9102
No log	23.0588	392	0.8048	0.6426	0.8048	0.8971
No log	23.1765	394	0.7667	0.6585	0.7667	0.8756
No log	23.2941	396	0.7494	0.6734	0.7494	0.8657
No log	23.4118	398	0.7757	0.6664	0.7757	0.8808
No log	23.5294	400	0.8185	0.6464	0.8185	0.9047
No log	23.6471	402	0.8383	0.6555	0.8383	0.9156
No log	23.7647	404	0.8884	0.6509	0.8884	0.9426
No log	23.8824	406	0.9242	0.6339	0.9242	0.9614
No log	24.0	408	0.8902	0.6296	0.8902	0.9435
No log	24.1176	410	0.8412	0.6288	0.8412	0.9172
No log	24.2353	412	0.8417	0.6483	0.8417	0.9174
No log	24.3529	414	0.8733	0.6148	0.8733	0.9345
No log	24.4706	416	0.9115	0.5778	0.9115	0.9547
No log	24.5882	418	0.8842	0.6158	0.8842	0.9403
No log	24.7059	420	0.8403	0.6379	0.8403	0.9167
No log	24.8235	422	0.7845	0.6511	0.7845	0.8857
No log	24.9412	424	0.7707	0.6337	0.7707	0.8779
No log	25.0588	426	0.7760	0.6551	0.7760	0.8809
No log	25.1765	428	0.8298	0.6409	0.8298	0.9109
No log	25.2941	430	0.8496	0.6235	0.8496	0.9218
No log	25.4118	432	0.8743	0.6044	0.8743	0.9350
No log	25.5294	434	0.8495	0.6168	0.8495	0.9217
No log	25.6471	436	0.8073	0.6531	0.8073	0.8985
No log	25.7647	438	0.8233	0.6540	0.8233	0.9074
No log	25.8824	440	0.8992	0.6135	0.8992	0.9482
No log	26.0	442	0.9770	0.5713	0.9770	0.9884
No log	26.1176	444	0.9950	0.5308	0.9950	0.9975
No log	26.2353	446	0.9310	0.5793	0.9310	0.9649
No log	26.3529	448	0.8242	0.6223	0.8242	0.9079
No log	26.4706	450	0.7436	0.6526	0.7436	0.8623
No log	26.5882	452	0.7292	0.6788	0.7292	0.8539
No log	26.7059	454	0.7545	0.6409	0.7545	0.8686
No log	26.8235	456	0.7999	0.6523	0.7999	0.8944
No log	26.9412	458	0.9140	0.6331	0.9140	0.9560
No log	27.0588	460	1.0601	0.5554	1.0601	1.0296
No log	27.1765	462	1.0883	0.5432	1.0883	1.0432
No log	27.2941	464	1.0143	0.5616	1.0143	1.0071
No log	27.4118	466	0.8777	0.6465	0.8777	0.9369
No log	27.5294	468	0.7547	0.6718	0.7547	0.8687
No log	27.6471	470	0.7124	0.6789	0.7124	0.8441
No log	27.7647	472	0.7066	0.6726	0.7066	0.8406
No log	27.8824	474	0.7309	0.6523	0.7309	0.8549
No log	28.0	476	0.7808	0.6602	0.7808	0.8837
No log	28.1176	478	0.8013	0.6287	0.8013	0.8952
No log	28.2353	480	0.7743	0.6646	0.7743	0.8799
No log	28.3529	482	0.7296	0.6623	0.7296	0.8542
No log	28.4706	484	0.7166	0.6614	0.7166	0.8465
No log	28.5882	486	0.7449	0.6807	0.7449	0.8631
No log	28.7059	488	0.8354	0.6597	0.8354	0.9140
No log	28.8235	490	0.9088	0.6530	0.9088	0.9533
No log	28.9412	492	0.9366	0.6337	0.9366	0.9678
No log	29.0588	494	0.9027	0.6426	0.9027	0.9501
No log	29.1765	496	0.8228	0.6451	0.8228	0.9071
No log	29.2941	498	0.7560	0.6723	0.7560	0.8695
0.5814	29.4118	500	0.7362	0.6710	0.7362	0.8580
0.5814	29.5294	502	0.7463	0.6676	0.7463	0.8639
0.5814	29.6471	504	0.7982	0.6379	0.7982	0.8934
0.5814	29.7647	506	0.8448	0.6553	0.8448	0.9192
0.5814	29.8824	508	0.8591	0.6521	0.8591	0.9269
0.5814	30.0	510	0.8759	0.6521	0.8759	0.9359

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.2.0
• Tokenizers 0.19.1