ArabicNewSplits6_FineTuningAraBERTFreeze_run2_AugV5_k3_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: 0.8744
• Qwk: 0.5993
• Mse: 0.8744
• Rmse: 0.9351

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	0.2222	2	7.8770	-0.0446	7.8770	2.8066
No log	0.4444	4	5.5181	-0.0349	5.5181	2.3491
No log	0.6667	6	3.8834	0.0290	3.8834	1.9706
No log	0.8889	8	2.9086	0.1081	2.9086	1.7055
No log	1.1111	10	2.2144	0.1862	2.2144	1.4881
No log	1.3333	12	1.6827	0.1687	1.6827	1.2972
No log	1.5556	14	1.3924	0.2195	1.3924	1.1800
No log	1.7778	16	1.2864	0.1307	1.2864	1.1342
No log	2.0	18	1.2108	0.2529	1.2108	1.1003
No log	2.2222	20	1.1752	0.1813	1.1752	1.0841
No log	2.4444	22	1.1256	0.2535	1.1256	1.0609
No log	2.6667	24	1.0318	0.3459	1.0318	1.0158
No log	2.8889	26	0.9921	0.3940	0.9921	0.9961
No log	3.1111	28	1.0290	0.4194	1.0290	1.0144
No log	3.3333	30	1.0054	0.4283	1.0054	1.0027
No log	3.5556	32	0.9390	0.4194	0.9390	0.9690
No log	3.7778	34	0.8870	0.4136	0.8870	0.9418
No log	4.0	36	0.8635	0.4064	0.8635	0.9292
No log	4.2222	38	0.8526	0.4554	0.8526	0.9233
No log	4.4444	40	0.8459	0.4554	0.8459	0.9197
No log	4.6667	42	0.8499	0.4698	0.8499	0.9219
No log	4.8889	44	0.8398	0.4747	0.8398	0.9164
No log	5.1111	46	0.8139	0.4847	0.8139	0.9022
No log	5.3333	48	0.7907	0.4868	0.7907	0.8892
No log	5.5556	50	0.7777	0.5360	0.7777	0.8819
No log	5.7778	52	0.7829	0.5828	0.7829	0.8848
No log	6.0	54	0.7564	0.6037	0.7564	0.8697
No log	6.2222	56	0.7767	0.6238	0.7767	0.8813
No log	6.4444	58	0.8226	0.5818	0.8226	0.9070
No log	6.6667	60	0.7679	0.6205	0.7679	0.8763
No log	6.8889	62	0.7128	0.6459	0.7128	0.8442
No log	7.1111	64	0.6919	0.6522	0.6919	0.8318
No log	7.3333	66	0.6923	0.6300	0.6923	0.8321
No log	7.5556	68	0.6746	0.6367	0.6746	0.8214
No log	7.7778	70	0.7238	0.6229	0.7238	0.8508
No log	8.0	72	0.7420	0.6152	0.7420	0.8614
No log	8.2222	74	0.6861	0.6111	0.6861	0.8283
No log	8.4444	76	0.6603	0.6527	0.6603	0.8126
No log	8.6667	78	0.6656	0.6548	0.6656	0.8159
No log	8.8889	80	0.6583	0.6723	0.6583	0.8113
No log	9.1111	82	0.6595	0.6792	0.6595	0.8121
No log	9.3333	84	0.6984	0.6599	0.6984	0.8357
No log	9.5556	86	0.7270	0.6352	0.7270	0.8527
No log	9.7778	88	0.7133	0.6560	0.7133	0.8446
No log	10.0	90	0.6981	0.6704	0.6981	0.8355
No log	10.2222	92	0.6986	0.6851	0.6986	0.8358
No log	10.4444	94	0.7527	0.6615	0.7527	0.8676
No log	10.6667	96	0.7440	0.6691	0.7440	0.8625
No log	10.8889	98	0.6705	0.6676	0.6705	0.8188
No log	11.1111	100	0.6714	0.6610	0.6714	0.8194
No log	11.3333	102	0.6956	0.6378	0.6956	0.8340
No log	11.5556	104	0.6775	0.6722	0.6775	0.8231
No log	11.7778	106	0.7066	0.6718	0.7066	0.8406
No log	12.0	108	0.7638	0.6767	0.7638	0.8739
No log	12.2222	110	0.7626	0.6767	0.7626	0.8733
No log	12.4444	112	0.7075	0.6632	0.7075	0.8411
No log	12.6667	114	0.6867	0.6789	0.6867	0.8287
No log	12.8889	116	0.6849	0.6399	0.6849	0.8276
No log	13.1111	118	0.6695	0.6856	0.6695	0.8183
No log	13.3333	120	0.6664	0.7079	0.6664	0.8163
No log	13.5556	122	0.7066	0.6905	0.7066	0.8406
No log	13.7778	124	0.7271	0.6932	0.7271	0.8527
No log	14.0	126	0.7103	0.7107	0.7103	0.8428
No log	14.2222	128	0.7027	0.6961	0.7027	0.8383
No log	14.4444	130	0.7039	0.7047	0.7039	0.8390
No log	14.6667	132	0.7039	0.6908	0.7039	0.8390
No log	14.8889	134	0.7159	0.7122	0.7159	0.8461
No log	15.1111	136	0.7400	0.6785	0.7400	0.8603
No log	15.3333	138	0.7482	0.6742	0.7482	0.8650
No log	15.5556	140	0.7381	0.6943	0.7381	0.8591
No log	15.7778	142	0.7337	0.7114	0.7337	0.8566
No log	16.0	144	0.7898	0.6124	0.7898	0.8887
No log	16.2222	146	0.8194	0.6004	0.8194	0.9052
No log	16.4444	148	0.7723	0.6055	0.7723	0.8788
No log	16.6667	150	0.7144	0.7013	0.7144	0.8452
No log	16.8889	152	0.7795	0.6583	0.7795	0.8829
No log	17.1111	154	0.8422	0.6160	0.8422	0.9177
No log	17.3333	156	0.8044	0.6621	0.8044	0.8969
No log	17.5556	158	0.7481	0.7072	0.7481	0.8649
No log	17.7778	160	0.7518	0.6616	0.7518	0.8671
No log	18.0	162	0.7719	0.6371	0.7719	0.8786
No log	18.2222	164	0.7735	0.6175	0.7735	0.8795
No log	18.4444	166	0.7334	0.6644	0.7334	0.8564
No log	18.6667	168	0.6981	0.7236	0.6981	0.8355
No log	18.8889	170	0.6963	0.6929	0.6963	0.8344
No log	19.1111	172	0.6976	0.7190	0.6976	0.8352
No log	19.3333	174	0.7096	0.6952	0.7096	0.8424
No log	19.5556	176	0.7106	0.6952	0.7106	0.8430
No log	19.7778	178	0.7211	0.6997	0.7211	0.8492
No log	20.0	180	0.7512	0.6659	0.7512	0.8667
No log	20.2222	182	0.7723	0.6568	0.7723	0.8788
No log	20.4444	184	0.7881	0.6252	0.7881	0.8877
No log	20.6667	186	0.7854	0.6101	0.7854	0.8862
No log	20.8889	188	0.7995	0.6162	0.7995	0.8942
No log	21.1111	190	0.7787	0.6227	0.7787	0.8825
No log	21.3333	192	0.7537	0.6292	0.7537	0.8682
No log	21.5556	194	0.7522	0.6857	0.7522	0.8673
No log	21.7778	196	0.7736	0.6671	0.7736	0.8795
No log	22.0	198	0.8028	0.6548	0.8028	0.8960
No log	22.2222	200	0.8436	0.6549	0.8436	0.9185
No log	22.4444	202	0.8699	0.6272	0.8699	0.9327
No log	22.6667	204	0.8530	0.6111	0.8530	0.9236
No log	22.8889	206	0.7827	0.6186	0.7827	0.8847
No log	23.1111	208	0.7460	0.6782	0.7460	0.8637
No log	23.3333	210	0.7346	0.6835	0.7346	0.8571
No log	23.5556	212	0.7579	0.6426	0.7579	0.8706
No log	23.7778	214	0.8070	0.6415	0.8070	0.8983
No log	24.0	216	0.8278	0.6415	0.8278	0.9099
No log	24.2222	218	0.8021	0.6467	0.8021	0.8956
No log	24.4444	220	0.7617	0.6952	0.7617	0.8727
No log	24.6667	222	0.7554	0.6962	0.7554	0.8691
No log	24.8889	224	0.7321	0.7282	0.7321	0.8556
No log	25.1111	226	0.7249	0.6843	0.7249	0.8514
No log	25.3333	228	0.7526	0.6609	0.7526	0.8675
No log	25.5556	230	0.7559	0.6790	0.7559	0.8694
No log	25.7778	232	0.7485	0.6963	0.7485	0.8651
No log	26.0	234	0.7500	0.6889	0.7500	0.8660
No log	26.2222	236	0.7651	0.6765	0.7651	0.8747
No log	26.4444	238	0.7957	0.6637	0.7957	0.8920
No log	26.6667	240	0.8059	0.6511	0.8059	0.8977
No log	26.8889	242	0.8280	0.6313	0.8280	0.9100
No log	27.1111	244	0.8283	0.6220	0.8283	0.9101
No log	27.3333	246	0.8483	0.6094	0.8483	0.9210
No log	27.5556	248	0.8270	0.6276	0.8270	0.9094
No log	27.7778	250	0.7928	0.6705	0.7928	0.8904
No log	28.0	252	0.7977	0.6661	0.7977	0.8931
No log	28.2222	254	0.8055	0.6692	0.8055	0.8975
No log	28.4444	256	0.8186	0.6756	0.8186	0.9048
No log	28.6667	258	0.8511	0.6523	0.8511	0.9226
No log	28.8889	260	0.8957	0.6142	0.8957	0.9464
No log	29.1111	262	0.9312	0.6290	0.9312	0.9650
No log	29.3333	264	0.8861	0.6277	0.8861	0.9413
No log	29.5556	266	0.8357	0.6714	0.8357	0.9141
No log	29.7778	268	0.8102	0.6834	0.8102	0.9001
No log	30.0	270	0.7870	0.6902	0.7870	0.8871
No log	30.2222	272	0.7738	0.6701	0.7738	0.8797
No log	30.4444	274	0.7764	0.6701	0.7764	0.8812
No log	30.6667	276	0.7757	0.6701	0.7757	0.8807
No log	30.8889	278	0.8060	0.6635	0.8060	0.8978
No log	31.1111	280	0.8593	0.6523	0.8593	0.9270
No log	31.3333	282	0.8783	0.6436	0.8783	0.9372
No log	31.5556	284	0.8855	0.6363	0.8855	0.9410
No log	31.7778	286	0.8635	0.6638	0.8635	0.9292
No log	32.0	288	0.8608	0.6399	0.8608	0.9278
No log	32.2222	290	0.8461	0.6517	0.8461	0.9198
No log	32.4444	292	0.8181	0.6173	0.8181	0.9045
No log	32.6667	294	0.8052	0.6511	0.8052	0.8973
No log	32.8889	296	0.8112	0.6820	0.8112	0.9007
No log	33.1111	298	0.8131	0.6750	0.8131	0.9017
No log	33.3333	300	0.8262	0.6805	0.8262	0.9090
No log	33.5556	302	0.8369	0.6857	0.8369	0.9148
No log	33.7778	304	0.8348	0.6523	0.8348	0.9136
No log	34.0	306	0.8076	0.6451	0.8076	0.8986
No log	34.2222	308	0.7897	0.6409	0.7897	0.8887
No log	34.4444	310	0.7928	0.6615	0.7928	0.8904
No log	34.6667	312	0.8029	0.6703	0.8029	0.8960
No log	34.8889	314	0.8427	0.6576	0.8427	0.9180
No log	35.1111	316	0.8414	0.6511	0.8414	0.9173
No log	35.3333	318	0.8369	0.6495	0.8369	0.9148
No log	35.5556	320	0.8264	0.6474	0.8264	0.9091
No log	35.7778	322	0.8441	0.6151	0.8441	0.9187
No log	36.0	324	0.8510	0.6044	0.8510	0.9225
No log	36.2222	326	0.8482	0.6312	0.8482	0.9210
No log	36.4444	328	0.8601	0.6638	0.8601	0.9274
No log	36.6667	330	0.8731	0.6605	0.8731	0.9344
No log	36.8889	332	0.8811	0.6621	0.8811	0.9387
No log	37.1111	334	0.8706	0.6605	0.8706	0.9331
No log	37.3333	336	0.8810	0.6454	0.8810	0.9386
No log	37.5556	338	0.8644	0.6556	0.8644	0.9297
No log	37.7778	340	0.8795	0.6369	0.8795	0.9378
No log	38.0	342	0.8707	0.6360	0.8707	0.9331
No log	38.2222	344	0.8411	0.6261	0.8411	0.9171
No log	38.4444	346	0.8025	0.6472	0.8025	0.8958
No log	38.6667	348	0.7692	0.6757	0.7692	0.8770
No log	38.8889	350	0.7534	0.6953	0.7534	0.8680
No log	39.1111	352	0.7650	0.6788	0.7650	0.8747
No log	39.3333	354	0.8008	0.6609	0.8008	0.8949
No log	39.5556	356	0.9075	0.6131	0.9075	0.9527
No log	39.7778	358	0.9882	0.5893	0.9882	0.9941
No log	40.0	360	1.0072	0.5937	1.0072	1.0036
No log	40.2222	362	0.9808	0.5987	0.9808	0.9904
No log	40.4444	364	0.9162	0.6297	0.9162	0.9572
No log	40.6667	366	0.8945	0.6418	0.8945	0.9458
No log	40.8889	368	0.9209	0.6011	0.9209	0.9596
No log	41.1111	370	0.9359	0.6170	0.9359	0.9674
No log	41.3333	372	0.9000	0.6382	0.9000	0.9487
No log	41.5556	374	0.8574	0.6198	0.8574	0.9260
No log	41.7778	376	0.8379	0.6035	0.8379	0.9154
No log	42.0	378	0.8057	0.6673	0.8057	0.8976
No log	42.2222	380	0.8109	0.6640	0.8109	0.9005
No log	42.4444	382	0.8330	0.6771	0.8330	0.9127
No log	42.6667	384	0.8610	0.6680	0.8610	0.9279
No log	42.8889	386	0.9226	0.6096	0.9226	0.9605
No log	43.1111	388	0.9577	0.5870	0.9577	0.9786
No log	43.3333	390	0.9608	0.6003	0.9608	0.9802
No log	43.5556	392	0.9434	0.6027	0.9434	0.9713
No log	43.7778	394	0.8994	0.6131	0.8994	0.9483
No log	44.0	396	0.8393	0.6434	0.8393	0.9161
No log	44.2222	398	0.8098	0.6685	0.8098	0.8999
No log	44.4444	400	0.8129	0.6746	0.8129	0.9016
No log	44.6667	402	0.8455	0.6522	0.8455	0.9195
No log	44.8889	404	0.8893	0.6473	0.8893	0.9430
No log	45.1111	406	0.9436	0.6194	0.9436	0.9714
No log	45.3333	408	0.9505	0.6194	0.9505	0.9749
No log	45.5556	410	0.9043	0.6328	0.9043	0.9509
No log	45.7778	412	0.8421	0.6772	0.8421	0.9177
No log	46.0	414	0.8315	0.6652	0.8315	0.9118
No log	46.2222	416	0.8313	0.6498	0.8313	0.9118
No log	46.4444	418	0.8472	0.6307	0.8472	0.9204
No log	46.6667	420	0.8637	0.6163	0.8637	0.9293
No log	46.8889	422	0.8965	0.6204	0.8965	0.9468
No log	47.1111	424	0.8928	0.6354	0.8928	0.9449
No log	47.3333	426	0.8987	0.6204	0.8987	0.9480
No log	47.5556	428	0.8989	0.6368	0.8989	0.9481
No log	47.7778	430	0.8979	0.6403	0.8979	0.9476
No log	48.0	432	0.9375	0.6163	0.9375	0.9683
No log	48.2222	434	0.9820	0.5946	0.9820	0.9910
No log	48.4444	436	0.9795	0.5946	0.9795	0.9897
No log	48.6667	438	0.9683	0.6207	0.9683	0.9840
No log	48.8889	440	0.9375	0.6262	0.9375	0.9682
No log	49.1111	442	0.9210	0.6444	0.9210	0.9597
No log	49.3333	444	0.9241	0.6270	0.9241	0.9613
No log	49.5556	446	0.9133	0.6251	0.9133	0.9557
No log	49.7778	448	0.8853	0.6434	0.8853	0.9409
No log	50.0	450	0.8890	0.6251	0.8890	0.9429
No log	50.2222	452	0.9062	0.6313	0.9062	0.9519
No log	50.4444	454	0.9333	0.6332	0.9333	0.9661
No log	50.6667	456	0.9216	0.6318	0.9216	0.9600
No log	50.8889	458	0.8969	0.6369	0.8969	0.9471
No log	51.1111	460	0.8674	0.6355	0.8674	0.9313
No log	51.3333	462	0.8631	0.6223	0.8631	0.9291
No log	51.5556	464	0.8765	0.6223	0.8765	0.9362
No log	51.7778	466	0.9074	0.6318	0.9074	0.9526
No log	52.0	468	0.9128	0.6113	0.9128	0.9554
No log	52.2222	470	0.9336	0.6063	0.9336	0.9663
No log	52.4444	472	0.9358	0.6144	0.9358	0.9674
No log	52.6667	474	0.9514	0.6102	0.9514	0.9754
No log	52.8889	476	0.9485	0.6136	0.9485	0.9739
No log	53.1111	478	0.9484	0.6102	0.9484	0.9738
No log	53.3333	480	0.9384	0.6233	0.9384	0.9687
No log	53.5556	482	0.9394	0.6226	0.9394	0.9692
No log	53.7778	484	0.8989	0.6233	0.8989	0.9481
No log	54.0	486	0.8607	0.6083	0.8607	0.9278
No log	54.2222	488	0.8613	0.6174	0.8613	0.9281
No log	54.4444	490	0.8942	0.6027	0.8942	0.9456
No log	54.6667	492	0.9210	0.6304	0.9210	0.9597
No log	54.8889	494	0.9468	0.6201	0.9468	0.9730
No log	55.1111	496	0.9394	0.6201	0.9394	0.9692
No log	55.3333	498	0.9151	0.6259	0.9151	0.9566
0.4992	55.5556	500	0.8934	0.6276	0.8934	0.9452
0.4992	55.7778	502	0.8745	0.6167	0.8745	0.9352
0.4992	56.0	504	0.8666	0.6496	0.8666	0.9309
0.4992	56.2222	506	0.8706	0.6519	0.8706	0.9330
0.4992	56.4444	508	0.8989	0.6369	0.8989	0.9481
0.4992	56.6667	510	0.9489	0.6173	0.9489	0.9741
0.4992	56.8889	512	0.9726	0.6141	0.9726	0.9862
0.4992	57.1111	514	0.9589	0.6153	0.9589	0.9792
0.4992	57.3333	516	0.9188	0.6231	0.9188	0.9586
0.4992	57.5556	518	0.8744	0.5993	0.8744	0.9351

Framework versions

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