ArabicNewSplits6_FineTuningAraBERTFreeze_run2_AugV5_k4_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: 0.9291
• Qwk: 0.6337
• Mse: 0.9291
• Rmse: 0.9639

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	0.1667	2	7.8271	-0.0460	7.8271	2.7977
No log	0.3333	4	5.4951	-0.0378	5.4951	2.3442
No log	0.5	6	3.8880	0.0347	3.8880	1.9718
No log	0.6667	8	2.9475	0.1022	2.9475	1.7168
No log	0.8333	10	2.2145	0.1862	2.2145	1.4881
No log	1.0	12	1.6432	0.1309	1.6432	1.2819
No log	1.1667	14	1.3285	0.2906	1.3285	1.1526
No log	1.3333	16	1.1438	0.3399	1.1438	1.0695
No log	1.5	18	1.0531	0.4598	1.0531	1.0262
No log	1.6667	20	1.0157	0.4564	1.0157	1.0078
No log	1.8333	22	0.9730	0.3916	0.9730	0.9864
No log	2.0	24	0.9628	0.4106	0.9628	0.9812
No log	2.1667	26	0.9774	0.4652	0.9774	0.9886
No log	2.3333	28	1.0013	0.4764	1.0013	1.0007
No log	2.5	30	0.9819	0.4764	0.9819	0.9909
No log	2.6667	32	0.9789	0.4829	0.9789	0.9894
No log	2.8333	34	0.9305	0.5002	0.9305	0.9646
No log	3.0	36	0.8819	0.4929	0.8819	0.9391
No log	3.1667	38	0.8406	0.5070	0.8406	0.9168
No log	3.3333	40	0.7922	0.4836	0.7922	0.8901
No log	3.5	42	0.7784	0.5470	0.7784	0.8823
No log	3.6667	44	0.7880	0.5693	0.7880	0.8877
No log	3.8333	46	0.7958	0.6011	0.7958	0.8921
No log	4.0	48	0.9102	0.5916	0.9102	0.9540
No log	4.1667	50	1.0421	0.4921	1.0421	1.0208
No log	4.3333	52	1.0013	0.5133	1.0013	1.0006
No log	4.5	54	0.8144	0.6314	0.8144	0.9024
No log	4.6667	56	0.7461	0.5924	0.7461	0.8638
No log	4.8333	58	0.7397	0.5722	0.7397	0.8601
No log	5.0	60	0.7374	0.6087	0.7374	0.8587
No log	5.1667	62	0.7283	0.6212	0.7283	0.8534
No log	5.3333	64	0.7808	0.6300	0.7808	0.8836
No log	5.5	66	0.8824	0.5821	0.8824	0.9393
No log	5.6667	68	0.8647	0.6069	0.8647	0.9299
No log	5.8333	70	0.7770	0.6308	0.7770	0.8814
No log	6.0	72	0.7153	0.6558	0.7153	0.8458
No log	6.1667	74	0.6965	0.6645	0.6965	0.8346
No log	6.3333	76	0.7088	0.6520	0.7088	0.8419
No log	6.5	78	0.8145	0.6438	0.8145	0.9025
No log	6.6667	80	0.9677	0.4980	0.9677	0.9837
No log	6.8333	82	0.8844	0.5738	0.8844	0.9404
No log	7.0	84	0.7356	0.6614	0.7356	0.8577
No log	7.1667	86	0.6683	0.7306	0.6683	0.8175
No log	7.3333	88	0.6858	0.7120	0.6858	0.8281
No log	7.5	90	0.7340	0.6716	0.7340	0.8567
No log	7.6667	92	0.7009	0.6947	0.7009	0.8372
No log	7.8333	94	0.7005	0.6657	0.7005	0.8370
No log	8.0	96	0.7662	0.6564	0.7662	0.8753
No log	8.1667	98	0.7676	0.6564	0.7676	0.8761
No log	8.3333	100	0.7281	0.6467	0.7281	0.8533
No log	8.5	102	0.7196	0.6841	0.7196	0.8483
No log	8.6667	104	0.6933	0.7148	0.6933	0.8326
No log	8.8333	106	0.7361	0.6849	0.7361	0.8580
No log	9.0	108	0.8213	0.6364	0.8213	0.9062
No log	9.1667	110	0.8531	0.6032	0.8531	0.9237
No log	9.3333	112	0.7745	0.6423	0.7745	0.8800
No log	9.5	114	0.7053	0.7088	0.7053	0.8398
No log	9.6667	116	0.7100	0.7031	0.7100	0.8426
No log	9.8333	118	0.7282	0.7168	0.7282	0.8533
No log	10.0	120	0.7364	0.7136	0.7364	0.8582
No log	10.1667	122	0.7205	0.7198	0.7205	0.8488
No log	10.3333	124	0.7541	0.6748	0.7541	0.8684
No log	10.5	126	0.7544	0.6648	0.7544	0.8686
No log	10.6667	128	0.7165	0.6807	0.7165	0.8465
No log	10.8333	130	0.6953	0.7246	0.6953	0.8338
No log	11.0	132	0.8197	0.6110	0.8197	0.9054
No log	11.1667	134	0.9760	0.5233	0.9760	0.9879
No log	11.3333	136	0.9171	0.5412	0.9171	0.9577
No log	11.5	138	0.7523	0.6587	0.7523	0.8674
No log	11.6667	140	0.7099	0.6943	0.7099	0.8426
No log	11.8333	142	0.7481	0.6730	0.7481	0.8649
No log	12.0	144	0.7348	0.6831	0.7348	0.8572
No log	12.1667	146	0.7378	0.7022	0.7378	0.8589
No log	12.3333	148	0.7460	0.7209	0.7460	0.8637
No log	12.5	150	0.7504	0.7270	0.7504	0.8663
No log	12.6667	152	0.7575	0.7451	0.7575	0.8703
No log	12.8333	154	0.7493	0.6962	0.7493	0.8656
No log	13.0	156	0.7705	0.6438	0.7705	0.8778
No log	13.1667	158	0.7331	0.6835	0.7331	0.8562
No log	13.3333	160	0.6997	0.7161	0.6997	0.8365
No log	13.5	162	0.7461	0.6681	0.7461	0.8638
No log	13.6667	164	0.7927	0.6339	0.7927	0.8904
No log	13.8333	166	0.7649	0.6576	0.7649	0.8746
No log	14.0	168	0.7280	0.6924	0.7280	0.8532
No log	14.1667	170	0.7437	0.6979	0.7437	0.8624
No log	14.3333	172	0.7618	0.7053	0.7618	0.8728
No log	14.5	174	0.7809	0.7164	0.7809	0.8837
No log	14.6667	176	0.7976	0.6668	0.7976	0.8931
No log	14.8333	178	0.7810	0.6798	0.7810	0.8837
No log	15.0	180	0.7880	0.6849	0.7880	0.8877
No log	15.1667	182	0.8563	0.6265	0.8563	0.9254
No log	15.3333	184	0.8388	0.6263	0.8388	0.9159
No log	15.5	186	0.7574	0.6748	0.7574	0.8703
No log	15.6667	188	0.7771	0.6637	0.7771	0.8815
No log	15.8333	190	0.8180	0.6536	0.8180	0.9044
No log	16.0	192	0.8046	0.6444	0.8046	0.8970
No log	16.1667	194	0.7703	0.6902	0.7703	0.8777
No log	16.3333	196	0.7910	0.6741	0.7910	0.8894
No log	16.5	198	0.8147	0.6604	0.8147	0.9026
No log	16.6667	200	0.7974	0.6887	0.7974	0.8930
No log	16.8333	202	0.8117	0.6839	0.8117	0.9009
No log	17.0	204	0.8606	0.6349	0.8606	0.9277
No log	17.1667	206	0.8866	0.6169	0.8866	0.9416
No log	17.3333	208	0.8312	0.6441	0.8312	0.9117
No log	17.5	210	0.7647	0.7022	0.7647	0.8745
No log	17.6667	212	0.7438	0.7191	0.7438	0.8625
No log	17.8333	214	0.7386	0.7278	0.7386	0.8594
No log	18.0	216	0.7400	0.6970	0.7400	0.8602
No log	18.1667	218	0.7593	0.6461	0.7593	0.8714
No log	18.3333	220	0.7479	0.6554	0.7479	0.8648
No log	18.5	222	0.7339	0.6907	0.7339	0.8567
No log	18.6667	224	0.7321	0.6859	0.7321	0.8556
No log	18.8333	226	0.7660	0.6762	0.7660	0.8752
No log	19.0	228	0.7839	0.6770	0.7839	0.8854
No log	19.1667	230	0.7614	0.6843	0.7614	0.8726
No log	19.3333	232	0.7966	0.6445	0.7966	0.8925
No log	19.5	234	0.7931	0.6445	0.7931	0.8906
No log	19.6667	236	0.7507	0.6842	0.7507	0.8664
No log	19.8333	238	0.7638	0.6661	0.7638	0.8740
No log	20.0	240	0.7788	0.6724	0.7788	0.8825
No log	20.1667	242	0.8063	0.6655	0.8063	0.8980
No log	20.3333	244	0.8049	0.6768	0.8049	0.8972
No log	20.5	246	0.7965	0.6741	0.7965	0.8925
No log	20.6667	248	0.8098	0.6696	0.8098	0.8999
No log	20.8333	250	0.8216	0.6719	0.8216	0.9064
No log	21.0	252	0.8337	0.6768	0.8337	0.9131
No log	21.1667	254	0.8240	0.6707	0.8240	0.9077
No log	21.3333	256	0.8192	0.6717	0.8192	0.9051
No log	21.5	258	0.8042	0.6618	0.8042	0.8967
No log	21.6667	260	0.7922	0.6809	0.7922	0.8901
No log	21.8333	262	0.8222	0.6809	0.8222	0.9067
No log	22.0	264	0.8803	0.6496	0.8803	0.9382
No log	22.1667	266	0.8647	0.6419	0.8647	0.9299
No log	22.3333	268	0.8799	0.6489	0.8799	0.9380
No log	22.5	270	0.8461	0.6556	0.8461	0.9199
No log	22.6667	272	0.7721	0.6586	0.7721	0.8787
No log	22.8333	274	0.7612	0.6458	0.7612	0.8725
No log	23.0	276	0.7594	0.6458	0.7594	0.8715
No log	23.1667	278	0.7497	0.6843	0.7497	0.8659
No log	23.3333	280	0.8236	0.6664	0.8236	0.9075
No log	23.5	282	0.8864	0.6509	0.8864	0.9415
No log	23.6667	284	0.8552	0.6650	0.8552	0.9248
No log	23.8333	286	0.7999	0.6570	0.7999	0.8944
No log	24.0	288	0.7892	0.6766	0.7892	0.8884
No log	24.1667	290	0.8074	0.6463	0.8074	0.8986
No log	24.3333	292	0.8426	0.6487	0.8426	0.9179
No log	24.5	294	0.8397	0.6637	0.8397	0.9163
No log	24.6667	296	0.7981	0.6456	0.7981	0.8933
No log	24.8333	298	0.7713	0.7022	0.7713	0.8782
No log	25.0	300	0.7714	0.6968	0.7714	0.8783
No log	25.1667	302	0.7887	0.6704	0.7887	0.8881
No log	25.3333	304	0.8148	0.6666	0.8148	0.9026
No log	25.5	306	0.7922	0.6332	0.7922	0.8901
No log	25.6667	308	0.7993	0.6407	0.7993	0.8941
No log	25.8333	310	0.8229	0.6407	0.8229	0.9072
No log	26.0	312	0.8599	0.6316	0.8599	0.9273
No log	26.1667	314	0.8579	0.6316	0.8579	0.9262
No log	26.3333	316	0.8536	0.6493	0.8536	0.9239
No log	26.5	318	0.8357	0.6496	0.8357	0.9142
No log	26.6667	320	0.8137	0.6569	0.8137	0.9020
No log	26.8333	322	0.7761	0.6640	0.7761	0.8810
No log	27.0	324	0.7520	0.6737	0.7520	0.8672
No log	27.1667	326	0.7398	0.6722	0.7398	0.8601
No log	27.3333	328	0.7536	0.6489	0.7536	0.8681
No log	27.5	330	0.7899	0.6484	0.7899	0.8888
No log	27.6667	332	0.8544	0.6531	0.8544	0.9244
No log	27.8333	334	0.8793	0.6362	0.8793	0.9377
No log	28.0	336	0.8580	0.6316	0.8580	0.9263
No log	28.1667	338	0.8479	0.6298	0.8479	0.9208
No log	28.3333	340	0.8716	0.6240	0.8716	0.9336
No log	28.5	342	0.9001	0.6516	0.9001	0.9487
No log	28.6667	344	0.8744	0.6640	0.8744	0.9351
No log	28.8333	346	0.8278	0.6316	0.8278	0.9098
No log	29.0	348	0.8023	0.6446	0.8023	0.8957
No log	29.1667	350	0.8002	0.6360	0.8002	0.8945
No log	29.3333	352	0.8225	0.6577	0.8225	0.9069
No log	29.5	354	0.8544	0.6392	0.8544	0.9243
No log	29.6667	356	0.8703	0.6130	0.8703	0.9329
No log	29.8333	358	0.8713	0.6420	0.8713	0.9334
No log	30.0	360	0.8965	0.6279	0.8965	0.9468
No log	30.1667	362	0.9571	0.6549	0.9571	0.9783
No log	30.3333	364	0.9664	0.6473	0.9664	0.9831
No log	30.5	366	0.9085	0.6526	0.9085	0.9531
No log	30.6667	368	0.8534	0.6401	0.8534	0.9238
No log	30.8333	370	0.8363	0.6396	0.8363	0.9145
No log	31.0	372	0.8188	0.6682	0.8188	0.9049
No log	31.1667	374	0.8163	0.6845	0.8163	0.9035
No log	31.3333	376	0.8298	0.6893	0.8298	0.9109
No log	31.5	378	0.8405	0.6796	0.8405	0.9168
No log	31.6667	380	0.8436	0.6554	0.8436	0.9185
No log	31.8333	382	0.8555	0.6249	0.8555	0.9249
No log	32.0	384	0.8756	0.6305	0.8756	0.9357
No log	32.1667	386	0.8941	0.6524	0.8941	0.9455
No log	32.3333	388	0.9140	0.6283	0.9140	0.9560
No log	32.5	390	0.9386	0.6582	0.9386	0.9688
No log	32.6667	392	0.9034	0.6597	0.9034	0.9505
No log	32.8333	394	0.8873	0.6496	0.8873	0.9420
No log	33.0	396	0.8490	0.6778	0.8490	0.9214
No log	33.1667	398	0.8195	0.6592	0.8195	0.9053
No log	33.3333	400	0.8110	0.6681	0.8110	0.9006
No log	33.5	402	0.8261	0.6827	0.8261	0.9089
No log	33.6667	404	0.8464	0.6693	0.8464	0.9200
No log	33.8333	406	0.8715	0.6496	0.8715	0.9335
No log	34.0	408	0.8862	0.6562	0.8862	0.9414
No log	34.1667	410	0.9001	0.6504	0.9001	0.9487
No log	34.3333	412	0.9272	0.6369	0.9272	0.9629
No log	34.5	414	0.9212	0.6369	0.9212	0.9598
No log	34.6667	416	0.8842	0.6499	0.8842	0.9403
No log	34.8333	418	0.8526	0.6524	0.8526	0.9234
No log	35.0	420	0.8504	0.6533	0.8504	0.9222
No log	35.1667	422	0.8795	0.6320	0.8795	0.9378
No log	35.3333	424	0.8830	0.6346	0.8830	0.9397
No log	35.5	426	0.8575	0.6426	0.8575	0.9260
No log	35.6667	428	0.8285	0.6652	0.8285	0.9102
No log	35.8333	430	0.8364	0.6388	0.8364	0.9145
No log	36.0	432	0.8633	0.6358	0.8633	0.9292
No log	36.1667	434	0.9029	0.6446	0.9029	0.9502
No log	36.3333	436	0.9519	0.5972	0.9519	0.9757
No log	36.5	438	0.9720	0.5707	0.9720	0.9859
No log	36.6667	440	0.9397	0.5920	0.9397	0.9694
No log	36.8333	442	0.8831	0.6132	0.8831	0.9398
No log	37.0	444	0.8498	0.6592	0.8498	0.9219
No log	37.1667	446	0.8327	0.6528	0.8327	0.9125
No log	37.3333	448	0.8253	0.6592	0.8253	0.9085
No log	37.5	450	0.8400	0.6372	0.8400	0.9165
No log	37.6667	452	0.8817	0.6332	0.8817	0.9390
No log	37.8333	454	0.8965	0.6368	0.8965	0.9468
No log	38.0	456	0.8801	0.6466	0.8801	0.9381
No log	38.1667	458	0.8700	0.6311	0.8700	0.9327
No log	38.3333	460	0.8807	0.6269	0.8807	0.9385
No log	38.5	462	0.9146	0.6370	0.9146	0.9563
No log	38.6667	464	0.9218	0.6619	0.9218	0.9601
No log	38.8333	466	0.8882	0.6541	0.8882	0.9424
No log	39.0	468	0.8438	0.6671	0.8438	0.9186
No log	39.1667	470	0.8297	0.6602	0.8297	0.9109
No log	39.3333	472	0.8312	0.6802	0.8312	0.9117
No log	39.5	474	0.8483	0.6724	0.8483	0.9210
No log	39.6667	476	0.8579	0.6724	0.8579	0.9262
No log	39.8333	478	0.8632	0.6741	0.8632	0.9291
No log	40.0	480	0.8450	0.6558	0.8450	0.9192
No log	40.1667	482	0.8362	0.6403	0.8362	0.9144
No log	40.3333	484	0.8474	0.6456	0.8474	0.9206
No log	40.5	486	0.8604	0.6553	0.8604	0.9276
No log	40.6667	488	0.8734	0.6473	0.8734	0.9346
No log	40.8333	490	0.8722	0.6355	0.8722	0.9339
No log	41.0	492	0.8575	0.6279	0.8575	0.9260
No log	41.1667	494	0.8616	0.6616	0.8616	0.9282
No log	41.3333	496	0.8626	0.6620	0.8626	0.9288
No log	41.5	498	0.8680	0.6591	0.8680	0.9317
0.5301	41.6667	500	0.8786	0.6392	0.8786	0.9374
0.5301	41.8333	502	0.9181	0.6485	0.9181	0.9582
0.5301	42.0	504	1.0006	0.5893	1.0006	1.0003
0.5301	42.1667	506	1.0355	0.5685	1.0355	1.0176
0.5301	42.3333	508	0.9962	0.6050	0.9962	0.9981
0.5301	42.5	510	0.9079	0.6329	0.9079	0.9528
0.5301	42.6667	512	0.8318	0.6493	0.8318	0.9121
0.5301	42.8333	514	0.8032	0.6678	0.8032	0.8962
0.5301	43.0	516	0.7892	0.6678	0.7892	0.8884
0.5301	43.1667	518	0.7850	0.6797	0.7850	0.8860
0.5301	43.3333	520	0.8086	0.6852	0.8086	0.8992
0.5301	43.5	522	0.8514	0.6537	0.8514	0.9227
0.5301	43.6667	524	0.8791	0.6229	0.8791	0.9376
0.5301	43.8333	526	0.8799	0.6426	0.8799	0.9380
0.5301	44.0	528	0.8580	0.6625	0.8580	0.9263
0.5301	44.1667	530	0.8293	0.6678	0.8293	0.9107
0.5301	44.3333	532	0.8363	0.6703	0.8363	0.9145
0.5301	44.5	534	0.8590	0.6499	0.8590	0.9268
0.5301	44.6667	536	0.8842	0.6369	0.8842	0.9403
0.5301	44.8333	538	0.8763	0.6368	0.8763	0.9361
0.5301	45.0	540	0.8473	0.6436	0.8473	0.9205
0.5301	45.1667	542	0.8130	0.6446	0.8130	0.9016
0.5301	45.3333	544	0.7894	0.6764	0.7894	0.8885
0.5301	45.5	546	0.7927	0.6751	0.7927	0.8903
0.5301	45.6667	548	0.8098	0.6815	0.8098	0.8999
0.5301	45.8333	550	0.8469	0.6620	0.8469	0.9203
0.5301	46.0	552	0.9091	0.6538	0.9091	0.9535
0.5301	46.1667	554	0.9950	0.5861	0.9950	0.9975
0.5301	46.3333	556	1.0397	0.5564	1.0397	1.0197
0.5301	46.5	558	1.0488	0.5564	1.0488	1.0241
0.5301	46.6667	560	1.0020	0.5976	1.0020	1.0010
0.5301	46.8333	562	0.9291	0.6337	0.9291	0.9639

Framework versions

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