ArabicNewSplits6_FineTuningAraBERTFreeze_run3_AugV5_k7_task2_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: 0.7993
• Qwk: 0.5042
• Mse: 0.7993
• Rmse: 0.8940

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	0.1111	2	6.4064	-0.0278	6.4064	2.5311
No log	0.2222	4	4.2708	-0.0202	4.2708	2.0666
No log	0.3333	6	3.0195	0.0109	3.0195	1.7377
No log	0.4444	8	2.2104	0.0011	2.2104	1.4867
No log	0.5556	10	1.6962	-0.0230	1.6962	1.3024
No log	0.6667	12	1.5891	-0.0606	1.5891	1.2606
No log	0.7778	14	1.8380	-0.0946	1.8380	1.3557
No log	0.8889	16	1.8248	-0.0754	1.8248	1.3508
No log	1.0	18	1.5332	-0.0912	1.5332	1.2382
No log	1.1111	20	1.0875	-0.0446	1.0875	1.0428
No log	1.2222	22	0.8857	0.0893	0.8857	0.9411
No log	1.3333	24	0.7621	0.1372	0.7621	0.8730
No log	1.4444	26	0.6970	0.2065	0.6970	0.8349
No log	1.5556	28	0.6798	0.2202	0.6798	0.8245
No log	1.6667	30	0.6777	0.2507	0.6777	0.8232
No log	1.7778	32	0.7024	0.25	0.7024	0.8381
No log	1.8889	34	0.7598	0.1503	0.7598	0.8716
No log	2.0	36	0.8253	0.1020	0.8253	0.9085
No log	2.1111	38	0.8621	0.0480	0.8621	0.9285
No log	2.2222	40	0.8285	0.1485	0.8285	0.9102
No log	2.3333	42	0.7557	0.2327	0.7557	0.8693
No log	2.4444	44	0.7283	0.2052	0.7283	0.8534
No log	2.5556	46	0.6955	0.2850	0.6955	0.8340
No log	2.6667	48	0.6423	0.3193	0.6423	0.8015
No log	2.7778	50	0.6079	0.3286	0.6079	0.7797
No log	2.8889	52	0.5987	0.3413	0.5987	0.7737
No log	3.0	54	0.5957	0.3450	0.5957	0.7718
No log	3.1111	56	0.6008	0.3744	0.6008	0.7751
No log	3.2222	58	0.6175	0.3693	0.6175	0.7858
No log	3.3333	60	0.6037	0.3692	0.6037	0.7770
No log	3.4444	62	0.5944	0.3865	0.5944	0.7710
No log	3.5556	64	0.6076	0.4	0.6076	0.7795
No log	3.6667	66	0.6376	0.4397	0.6376	0.7985
No log	3.7778	68	0.6486	0.4397	0.6486	0.8053
No log	3.8889	70	0.6441	0.4859	0.6441	0.8025
No log	4.0	72	0.5994	0.4992	0.5994	0.7742
No log	4.1111	74	0.5580	0.4255	0.5580	0.7470
No log	4.2222	76	0.5382	0.4070	0.5382	0.7336
No log	4.3333	78	0.5288	0.4070	0.5288	0.7272
No log	4.4444	80	0.5205	0.3947	0.5205	0.7215
No log	4.5556	82	0.5310	0.4501	0.5310	0.7287
No log	4.6667	84	0.6057	0.5004	0.6057	0.7783
No log	4.7778	86	0.6857	0.3969	0.6857	0.8281
No log	4.8889	88	0.6577	0.4292	0.6577	0.8110
No log	5.0	90	0.5568	0.5190	0.5568	0.7462
No log	5.1111	92	0.5266	0.4822	0.5266	0.7257
No log	5.2222	94	0.5279	0.4595	0.5279	0.7266
No log	5.3333	96	0.5214	0.4793	0.5214	0.7221
No log	5.4444	98	0.5252	0.5019	0.5252	0.7247
No log	5.5556	100	0.5447	0.4695	0.5447	0.7381
No log	5.6667	102	0.5483	0.4977	0.5483	0.7404
No log	5.7778	104	0.5541	0.5041	0.5541	0.7444
No log	5.8889	106	0.5521	0.4956	0.5521	0.7430
No log	6.0	108	0.5369	0.4956	0.5369	0.7327
No log	6.1111	110	0.5194	0.4664	0.5194	0.7207
No log	6.2222	112	0.5179	0.4556	0.5179	0.7196
No log	6.3333	114	0.5218	0.5008	0.5218	0.7224
No log	6.4444	116	0.5302	0.5059	0.5302	0.7281
No log	6.5556	118	0.5364	0.5121	0.5364	0.7324
No log	6.6667	120	0.5582	0.5241	0.5582	0.7471
No log	6.7778	122	0.5940	0.5	0.5940	0.7707
No log	6.8889	124	0.6404	0.5590	0.6404	0.8003
No log	7.0	126	0.6301	0.5392	0.6301	0.7938
No log	7.1111	128	0.5724	0.5703	0.5724	0.7566
No log	7.2222	130	0.5322	0.5498	0.5322	0.7295
No log	7.3333	132	0.5324	0.5455	0.5324	0.7296
No log	7.4444	134	0.5285	0.5015	0.5285	0.7270
No log	7.5556	136	0.5198	0.5071	0.5198	0.7210
No log	7.6667	138	0.5234	0.4309	0.5234	0.7235
No log	7.7778	140	0.5207	0.4944	0.5207	0.7216
No log	7.8889	142	0.5256	0.5500	0.5256	0.7250
No log	8.0	144	0.5648	0.5622	0.5648	0.7515
No log	8.1111	146	0.6165	0.5544	0.6165	0.7851
No log	8.2222	148	0.6118	0.5544	0.6118	0.7822
No log	8.3333	150	0.5563	0.5606	0.5563	0.7458
No log	8.4444	152	0.5411	0.5378	0.5411	0.7356
No log	8.5556	154	0.5435	0.5758	0.5435	0.7372
No log	8.6667	156	0.5400	0.5075	0.5400	0.7349
No log	8.7778	158	0.5394	0.5363	0.5394	0.7344
No log	8.8889	160	0.5514	0.5568	0.5514	0.7426
No log	9.0	162	0.5612	0.5449	0.5612	0.7491
No log	9.1111	164	0.5756	0.5571	0.5756	0.7587
No log	9.2222	166	0.5902	0.5717	0.5902	0.7682
No log	9.3333	168	0.5818	0.5670	0.5818	0.7628
No log	9.4444	170	0.5673	0.5487	0.5673	0.7532
No log	9.5556	172	0.5755	0.5170	0.5755	0.7586
No log	9.6667	174	0.5854	0.5344	0.5854	0.7651
No log	9.7778	176	0.5868	0.5518	0.5868	0.7660
No log	9.8889	178	0.5999	0.5376	0.5999	0.7745
No log	10.0	180	0.6097	0.5673	0.6097	0.7808
No log	10.1111	182	0.6161	0.5567	0.6161	0.7849
No log	10.2222	184	0.6306	0.5637	0.6306	0.7941
No log	10.3333	186	0.6352	0.5633	0.6352	0.7970
No log	10.4444	188	0.6271	0.5825	0.6271	0.7919
No log	10.5556	190	0.6317	0.5701	0.6317	0.7948
No log	10.6667	192	0.6470	0.5455	0.6470	0.8044
No log	10.7778	194	0.6473	0.5555	0.6473	0.8045
No log	10.8889	196	0.6509	0.5484	0.6509	0.8068
No log	11.0	198	0.6508	0.5239	0.6508	0.8067
No log	11.1111	200	0.6569	0.5776	0.6569	0.8105
No log	11.2222	202	0.6672	0.5577	0.6672	0.8168
No log	11.3333	204	0.6631	0.5384	0.6631	0.8143
No log	11.4444	206	0.6643	0.5384	0.6643	0.8150
No log	11.5556	208	0.6786	0.5475	0.6786	0.8238
No log	11.6667	210	0.6767	0.5636	0.6767	0.8226
No log	11.7778	212	0.6805	0.5504	0.6805	0.8249
No log	11.8889	214	0.6901	0.5589	0.6901	0.8307
No log	12.0	216	0.6995	0.5879	0.6995	0.8364
No log	12.1111	218	0.6917	0.5897	0.6917	0.8317
No log	12.2222	220	0.6974	0.5897	0.6974	0.8351
No log	12.3333	222	0.6978	0.5435	0.6978	0.8353
No log	12.4444	224	0.6911	0.5476	0.6911	0.8313
No log	12.5556	226	0.6783	0.5169	0.6783	0.8236
No log	12.6667	228	0.6812	0.5421	0.6812	0.8253
No log	12.7778	230	0.6801	0.5116	0.6801	0.8247
No log	12.8889	232	0.6871	0.5058	0.6871	0.8289
No log	13.0	234	0.6925	0.5390	0.6925	0.8322
No log	13.1111	236	0.6968	0.5467	0.6968	0.8348
No log	13.2222	238	0.7100	0.5331	0.7100	0.8426
No log	13.3333	240	0.7252	0.5614	0.7252	0.8516
No log	13.4444	242	0.7285	0.5547	0.7285	0.8535
No log	13.5556	244	0.7202	0.5465	0.7202	0.8486
No log	13.6667	246	0.7125	0.5750	0.7125	0.8441
No log	13.7778	248	0.7077	0.5825	0.7077	0.8412
No log	13.8889	250	0.7119	0.5858	0.7119	0.8437
No log	14.0	252	0.7291	0.5825	0.7291	0.8539
No log	14.1111	254	0.7012	0.5858	0.7012	0.8374
No log	14.2222	256	0.6830	0.5714	0.6830	0.8264
No log	14.3333	258	0.6822	0.5871	0.6822	0.8260
No log	14.4444	260	0.6826	0.5538	0.6826	0.8262
No log	14.5556	262	0.6797	0.5323	0.6797	0.8245
No log	14.6667	264	0.6978	0.5271	0.6978	0.8353
No log	14.7778	266	0.7686	0.5144	0.7686	0.8767
No log	14.8889	268	0.8271	0.5089	0.8271	0.9094
No log	15.0	270	0.7931	0.5244	0.7931	0.8906
No log	15.1111	272	0.7340	0.5676	0.7340	0.8568
No log	15.2222	274	0.7294	0.5319	0.7294	0.8540
No log	15.3333	276	0.7403	0.5204	0.7403	0.8604
No log	15.4444	278	0.7539	0.5294	0.7539	0.8683
No log	15.5556	280	0.7570	0.5286	0.7570	0.8701
No log	15.6667	282	0.7535	0.5385	0.7535	0.8681
No log	15.7778	284	0.7656	0.5071	0.7656	0.8750
No log	15.8889	286	0.7687	0.5246	0.7687	0.8768
No log	16.0	288	0.7699	0.5257	0.7699	0.8774
No log	16.1111	290	0.7632	0.5505	0.7632	0.8736
No log	16.2222	292	0.7633	0.5505	0.7633	0.8737
No log	16.3333	294	0.7422	0.5572	0.7422	0.8615
No log	16.4444	296	0.7136	0.5600	0.7136	0.8447
No log	16.5556	298	0.7054	0.5429	0.7054	0.8399
No log	16.6667	300	0.7048	0.5281	0.7048	0.8395
No log	16.7778	302	0.7040	0.5320	0.7040	0.8390
No log	16.8889	304	0.6959	0.5454	0.6959	0.8342
No log	17.0	306	0.6939	0.5494	0.6939	0.8330
No log	17.1111	308	0.7085	0.5572	0.7085	0.8417
No log	17.2222	310	0.7450	0.5584	0.7450	0.8631
No log	17.3333	312	0.7607	0.5584	0.7607	0.8722
No log	17.4444	314	0.7485	0.5584	0.7485	0.8652
No log	17.5556	316	0.7359	0.5503	0.7359	0.8578
No log	17.6667	318	0.7136	0.5358	0.7136	0.8447
No log	17.7778	320	0.7247	0.5749	0.7247	0.8513
No log	17.8889	322	0.7203	0.5632	0.7203	0.8487
No log	18.0	324	0.7033	0.5196	0.7033	0.8386
No log	18.1111	326	0.7157	0.5572	0.7157	0.8460
No log	18.2222	328	0.7569	0.5331	0.7569	0.8700
No log	18.3333	330	0.7509	0.5464	0.7509	0.8666
No log	18.4444	332	0.7259	0.5414	0.7259	0.8520
No log	18.5556	334	0.6966	0.5551	0.6966	0.8346
No log	18.6667	336	0.7211	0.5504	0.7211	0.8492
No log	18.7778	338	0.7284	0.5556	0.7284	0.8535
No log	18.8889	340	0.7133	0.5634	0.7133	0.8446
No log	19.0	342	0.7306	0.5341	0.7306	0.8548
No log	19.1111	344	0.7631	0.5288	0.7631	0.8736
No log	19.2222	346	0.7635	0.5407	0.7635	0.8738
No log	19.3333	348	0.7529	0.5412	0.7529	0.8677
No log	19.4444	350	0.7287	0.5424	0.7287	0.8536
No log	19.5556	352	0.7348	0.5249	0.7348	0.8572
No log	19.6667	354	0.7343	0.4956	0.7343	0.8569
No log	19.7778	356	0.7447	0.4882	0.7447	0.8630
No log	19.8889	358	0.7828	0.5360	0.7828	0.8848
No log	20.0	360	0.8232	0.5309	0.8232	0.9073
No log	20.1111	362	0.8186	0.5149	0.8186	0.9048
No log	20.2222	364	0.7788	0.5211	0.7788	0.8825
No log	20.3333	366	0.7547	0.5132	0.7547	0.8687
No log	20.4444	368	0.7525	0.5456	0.7525	0.8675
No log	20.5556	370	0.7596	0.5123	0.7596	0.8716
No log	20.6667	372	0.7542	0.5315	0.7542	0.8684
No log	20.7778	374	0.7695	0.5186	0.7695	0.8772
No log	20.8889	376	0.7695	0.5206	0.7695	0.8772
No log	21.0	378	0.7616	0.5484	0.7616	0.8727
No log	21.1111	380	0.7453	0.5419	0.7453	0.8633
No log	21.2222	382	0.7321	0.5752	0.7321	0.8557
No log	21.3333	384	0.7184	0.5620	0.7184	0.8476
No log	21.4444	386	0.7315	0.5179	0.7315	0.8553
No log	21.5556	388	0.7683	0.5141	0.7683	0.8765
No log	21.6667	390	0.7633	0.5147	0.7633	0.8737
No log	21.7778	392	0.7179	0.4934	0.7179	0.8473
No log	21.8889	394	0.6844	0.4880	0.6844	0.8273
No log	22.0	396	0.6956	0.5016	0.6956	0.8340
No log	22.1111	398	0.7318	0.5176	0.7318	0.8555
No log	22.2222	400	0.7779	0.5146	0.7779	0.8820
No log	22.3333	402	0.8461	0.5309	0.8461	0.9198
No log	22.4444	404	0.8618	0.5234	0.8618	0.9283
No log	22.5556	406	0.8525	0.5369	0.8525	0.9233
No log	22.6667	408	0.8463	0.5398	0.8463	0.9200
No log	22.7778	410	0.8142	0.4974	0.8142	0.9024
No log	22.8889	412	0.7814	0.4807	0.7814	0.8840
No log	23.0	414	0.7598	0.4828	0.7598	0.8717
No log	23.1111	416	0.7408	0.4812	0.7408	0.8607
No log	23.2222	418	0.7408	0.4961	0.7408	0.8607
No log	23.3333	420	0.7321	0.4936	0.7321	0.8556
No log	23.4444	422	0.7308	0.4973	0.7308	0.8549
No log	23.5556	424	0.7675	0.5045	0.7675	0.8761
No log	23.6667	426	0.7871	0.5013	0.7871	0.8872
No log	23.7778	428	0.7589	0.4976	0.7589	0.8711
No log	23.8889	430	0.7064	0.5159	0.7064	0.8405
No log	24.0	432	0.6852	0.4930	0.6852	0.8277
No log	24.1111	434	0.6928	0.5038	0.6928	0.8324
No log	24.2222	436	0.7225	0.5295	0.7225	0.8500
No log	24.3333	438	0.7537	0.5268	0.7537	0.8682
No log	24.4444	440	0.7554	0.5051	0.7554	0.8691
No log	24.5556	442	0.7458	0.4857	0.7458	0.8636
No log	24.6667	444	0.7404	0.5	0.7404	0.8605
No log	24.7778	446	0.7376	0.5080	0.7376	0.8588
No log	24.8889	448	0.7612	0.5012	0.7612	0.8725
No log	25.0	450	0.8027	0.5075	0.8027	0.8959
No log	25.1111	452	0.8254	0.5201	0.8254	0.9085
No log	25.2222	454	0.8296	0.5216	0.8296	0.9108
No log	25.3333	456	0.7818	0.5155	0.7818	0.8842
No log	25.4444	458	0.7516	0.5016	0.7516	0.8669
No log	25.5556	460	0.7484	0.5090	0.7484	0.8651
No log	25.6667	462	0.7491	0.5054	0.7491	0.8655
No log	25.7778	464	0.7552	0.5244	0.7552	0.8690
No log	25.8889	466	0.7570	0.5276	0.7570	0.8701
No log	26.0	468	0.7492	0.5155	0.7492	0.8656
No log	26.1111	470	0.7243	0.5130	0.7243	0.8511
No log	26.2222	472	0.7188	0.5016	0.7188	0.8478
No log	26.3333	474	0.7229	0.5121	0.7229	0.8502
No log	26.4444	476	0.7472	0.5558	0.7472	0.8644
No log	26.5556	478	0.7570	0.5398	0.7570	0.8700
No log	26.6667	480	0.7564	0.5377	0.7564	0.8697
No log	26.7778	482	0.7306	0.5081	0.7306	0.8547
No log	26.8889	484	0.7245	0.5155	0.7245	0.8512
No log	27.0	486	0.7426	0.5296	0.7426	0.8617
No log	27.1111	488	0.7589	0.5023	0.7589	0.8711
No log	27.2222	490	0.7824	0.5044	0.7824	0.8846
No log	27.3333	492	0.8245	0.54	0.8245	0.9080
No log	27.4444	494	0.8560	0.5455	0.8560	0.9252
No log	27.5556	496	0.8346	0.5329	0.8346	0.9135
No log	27.6667	498	0.8003	0.5157	0.8003	0.8946
0.545	27.7778	500	0.7716	0.5203	0.7716	0.8784
0.545	27.8889	502	0.7569	0.5031	0.7569	0.8700
0.545	28.0	504	0.7528	0.5123	0.7528	0.8676
0.545	28.1111	506	0.7600	0.5049	0.7600	0.8718
0.545	28.2222	508	0.8030	0.5137	0.8030	0.8961
0.545	28.3333	510	0.8463	0.5213	0.8463	0.9199
0.545	28.4444	512	0.8264	0.5233	0.8265	0.9091
0.545	28.5556	514	0.7806	0.5189	0.7806	0.8835
0.545	28.6667	516	0.7454	0.5087	0.7454	0.8633
0.545	28.7778	518	0.7419	0.5326	0.7419	0.8613
0.545	28.8889	520	0.7502	0.5216	0.7502	0.8662
0.545	29.0	522	0.7592	0.5075	0.7592	0.8713
0.545	29.1111	524	0.7932	0.5100	0.7932	0.8906
0.545	29.2222	526	0.8185	0.5175	0.8185	0.9047
0.545	29.3333	528	0.8150	0.5119	0.8150	0.9027
0.545	29.4444	530	0.7993	0.5042	0.7993	0.8940

Framework versions

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