ArabicNewSplits7_FineTuningAraBERT_run2_AugV5_k8_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: 0.8523
• Qwk: 0.5291
• Mse: 0.8523
• Rmse: 0.9232

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	0.0769	2	4.8459	0.0064	4.8459	2.2013
No log	0.1538	4	3.1151	-0.0625	3.1151	1.7650
No log	0.2308	6	1.7017	0.0504	1.7017	1.3045
No log	0.3077	8	1.5782	-0.0508	1.5782	1.2563
No log	0.3846	10	1.2904	0.0666	1.2904	1.1360
No log	0.4615	12	1.3527	-0.0757	1.3527	1.1630
No log	0.5385	14	1.6222	0.0	1.6222	1.2736
No log	0.6154	16	1.5780	0.0	1.5780	1.2562
No log	0.6923	18	1.3871	-0.0149	1.3871	1.1778
No log	0.7692	20	1.2612	0.1753	1.2612	1.1230
No log	0.8462	22	1.2350	0.1397	1.2350	1.1113
No log	0.9231	24	1.3712	0.0561	1.3712	1.1710
No log	1.0	26	1.3531	0.0342	1.3531	1.1632
No log	1.0769	28	1.2235	0.2886	1.2235	1.1061
No log	1.1538	30	1.1670	0.2784	1.1670	1.0803
No log	1.2308	32	1.1681	0.1458	1.1681	1.0808
No log	1.3077	34	1.1690	0.2584	1.1690	1.0812
No log	1.3846	36	1.1727	0.1638	1.1727	1.0829
No log	1.4615	38	1.2101	0.1865	1.2101	1.1000
No log	1.5385	40	1.2069	0.1735	1.2069	1.0986
No log	1.6154	42	1.1310	0.1809	1.1310	1.0635
No log	1.6923	44	1.0691	0.3421	1.0691	1.0340
No log	1.7692	46	1.1262	0.2364	1.1262	1.0612
No log	1.8462	48	1.1588	0.1458	1.1588	1.0765
No log	1.9231	50	1.3259	0.1260	1.3259	1.1515
No log	2.0	52	1.6164	0.0800	1.6164	1.2714
No log	2.0769	54	1.5475	0.1198	1.5475	1.2440
No log	2.1538	56	1.2395	0.1562	1.2395	1.1133
No log	2.2308	58	1.1374	0.2372	1.1374	1.0665
No log	2.3077	60	1.0502	0.2134	1.0502	1.0248
No log	2.3846	62	1.0714	0.3115	1.0714	1.0351
No log	2.4615	64	1.0774	0.4405	1.0774	1.0380
No log	2.5385	66	1.0479	0.4311	1.0479	1.0237
No log	2.6154	68	1.1094	0.2285	1.1094	1.0533
No log	2.6923	70	1.1676	0.1959	1.1676	1.0806
No log	2.7692	72	1.1497	0.2098	1.1497	1.0722
No log	2.8462	74	1.0347	0.4434	1.0347	1.0172
No log	2.9231	76	0.9888	0.4548	0.9888	0.9944
No log	3.0	78	0.9956	0.3543	0.9956	0.9978
No log	3.0769	80	1.0167	0.4872	1.0167	1.0083
No log	3.1538	82	1.0255	0.4589	1.0255	1.0126
No log	3.2308	84	0.9454	0.4711	0.9454	0.9723
No log	3.3077	86	0.9278	0.4667	0.9278	0.9632
No log	3.3846	88	0.9659	0.4045	0.9659	0.9828
No log	3.4615	90	0.9473	0.3956	0.9473	0.9733
No log	3.5385	92	0.9285	0.4656	0.9285	0.9636
No log	3.6154	94	1.1352	0.4692	1.1352	1.0655
No log	3.6923	96	1.3345	0.4284	1.3345	1.1552
No log	3.7692	98	1.1976	0.4565	1.1976	1.0943
No log	3.8462	100	0.9229	0.4714	0.9229	0.9607
No log	3.9231	102	0.9211	0.4941	0.9211	0.9597
No log	4.0	104	0.9215	0.4273	0.9215	0.9599
No log	4.0769	106	0.8645	0.3943	0.8645	0.9298
No log	4.1538	108	1.0037	0.4057	1.0037	1.0018
No log	4.2308	110	1.0831	0.4032	1.0831	1.0407
No log	4.3077	112	1.0123	0.4632	1.0123	1.0061
No log	4.3846	114	0.8750	0.4465	0.8750	0.9354
No log	4.4615	116	0.8090	0.4321	0.8090	0.8994
No log	4.5385	118	0.8092	0.5107	0.8092	0.8995
No log	4.6154	120	0.8268	0.4808	0.8268	0.9093
No log	4.6923	122	0.9227	0.48	0.9227	0.9606
No log	4.7692	124	0.9786	0.4668	0.9786	0.9892
No log	4.8462	126	0.8627	0.5094	0.8627	0.9288
No log	4.9231	128	0.8610	0.5263	0.8610	0.9279
No log	5.0	130	1.0890	0.4820	1.0890	1.0435
No log	5.0769	132	1.0302	0.4085	1.0302	1.0150
No log	5.1538	134	0.8506	0.4624	0.8506	0.9223
No log	5.2308	136	0.8470	0.4572	0.8470	0.9203
No log	5.3077	138	1.1211	0.4468	1.1211	1.0588
No log	5.3846	140	1.1397	0.4080	1.1397	1.0675
No log	5.4615	142	0.9935	0.4989	0.9935	0.9968
No log	5.5385	144	0.9023	0.4615	0.9023	0.9499
No log	5.6154	146	0.8695	0.5235	0.8695	0.9325
No log	5.6923	148	0.8556	0.4327	0.8556	0.9250
No log	5.7692	150	0.8852	0.4957	0.8852	0.9408
No log	5.8462	152	0.9624	0.5166	0.9624	0.9810
No log	5.9231	154	0.9426	0.4646	0.9426	0.9709
No log	6.0	156	0.8874	0.3908	0.8874	0.9420
No log	6.0769	158	0.8936	0.4534	0.8936	0.9453
No log	6.1538	160	0.9324	0.4308	0.9324	0.9656
No log	6.2308	162	0.9265	0.4563	0.9265	0.9625
No log	6.3077	164	0.8296	0.4385	0.8296	0.9108
No log	6.3846	166	0.9453	0.4790	0.9453	0.9722
No log	6.4615	168	1.1193	0.4784	1.1193	1.0580
No log	6.5385	170	1.0950	0.5066	1.0950	1.0464
No log	6.6154	172	0.9829	0.4435	0.9829	0.9914
No log	6.6923	174	0.8449	0.4575	0.8449	0.9192
No log	6.7692	176	0.8135	0.5393	0.8135	0.9019
No log	6.8462	178	0.8051	0.5399	0.8051	0.8972
No log	6.9231	180	0.8079	0.4593	0.8079	0.8988
No log	7.0	182	0.9452	0.5253	0.9452	0.9722
No log	7.0769	184	1.0207	0.5130	1.0207	1.0103
No log	7.1538	186	0.9554	0.5301	0.9554	0.9774
No log	7.2308	188	0.8847	0.4920	0.8847	0.9406
No log	7.3077	190	0.8339	0.3852	0.8339	0.9132
No log	7.3846	192	0.8182	0.4086	0.8182	0.9045
No log	7.4615	194	0.8248	0.3811	0.8248	0.9082
No log	7.5385	196	0.8742	0.3880	0.8742	0.9350
No log	7.6154	198	0.9309	0.5098	0.9309	0.9648
No log	7.6923	200	0.8919	0.5014	0.8919	0.9444
No log	7.7692	202	0.8280	0.4763	0.8280	0.9100
No log	7.8462	204	0.7940	0.5351	0.7940	0.8911
No log	7.9231	206	0.8916	0.5614	0.8916	0.9442
No log	8.0	208	1.1764	0.5491	1.1764	1.0846
No log	8.0769	210	1.2753	0.5082	1.2753	1.1293
No log	8.1538	212	1.0750	0.5341	1.0750	1.0368
No log	8.2308	214	0.8645	0.5738	0.8645	0.9298
No log	8.3077	216	0.8150	0.4726	0.8150	0.9028
No log	8.3846	218	0.8288	0.4144	0.8288	0.9104
No log	8.4615	220	0.8808	0.4006	0.8808	0.9385
No log	8.5385	222	0.9019	0.4108	0.9019	0.9497
No log	8.6154	224	0.9268	0.4722	0.9268	0.9627
No log	8.6923	226	0.8656	0.4754	0.8656	0.9304
No log	8.7692	228	0.8349	0.3685	0.8349	0.9137
No log	8.8462	230	0.9295	0.3806	0.9295	0.9641
No log	8.9231	232	0.9067	0.4235	0.9067	0.9522
No log	9.0	234	0.8420	0.3478	0.8420	0.9176
No log	9.0769	236	0.8342	0.3700	0.8342	0.9133
No log	9.1538	238	0.8546	0.4640	0.8546	0.9244
No log	9.2308	240	0.8246	0.3957	0.8246	0.9081
No log	9.3077	242	0.7933	0.4526	0.7933	0.8907
No log	9.3846	244	0.7914	0.4519	0.7914	0.8896
No log	9.4615	246	0.7891	0.4142	0.7891	0.8883
No log	9.5385	248	0.8098	0.4102	0.8098	0.8999
No log	9.6154	250	0.8212	0.4470	0.8212	0.9062
No log	9.6923	252	0.8030	0.4493	0.8030	0.8961
No log	9.7692	254	0.8240	0.4515	0.8240	0.9077
No log	9.8462	256	0.8534	0.4698	0.8534	0.9238
No log	9.9231	258	0.8574	0.4521	0.8574	0.9259
No log	10.0	260	0.8387	0.4554	0.8387	0.9158
No log	10.0769	262	0.8727	0.4590	0.8727	0.9342
No log	10.1538	264	0.9038	0.5210	0.9038	0.9507
No log	10.2308	266	0.8429	0.5012	0.8429	0.9181
No log	10.3077	268	0.7943	0.5249	0.7943	0.8912
No log	10.3846	270	0.7944	0.4593	0.7944	0.8913
No log	10.4615	272	0.7971	0.4502	0.7971	0.8928
No log	10.5385	274	0.7950	0.4069	0.7950	0.8916
No log	10.6154	276	0.8214	0.4726	0.8214	0.9063
No log	10.6923	278	0.8651	0.4507	0.8651	0.9301
No log	10.7692	280	0.8583	0.4420	0.8583	0.9265
No log	10.8462	282	0.8994	0.4354	0.8994	0.9484
No log	10.9231	284	0.8939	0.3926	0.8939	0.9455
No log	11.0	286	0.8937	0.3812	0.8937	0.9453
No log	11.0769	288	0.9485	0.3655	0.9485	0.9739
No log	11.1538	290	0.9778	0.3202	0.9778	0.9888
No log	11.2308	292	0.9504	0.3335	0.9504	0.9749
No log	11.3077	294	0.9324	0.3229	0.9324	0.9656
No log	11.3846	296	0.9047	0.3020	0.9047	0.9512
No log	11.4615	298	0.8983	0.2674	0.8983	0.9478
No log	11.5385	300	0.8991	0.2917	0.8991	0.9482
No log	11.6154	302	0.9043	0.3474	0.9043	0.9509
No log	11.6923	304	0.9005	0.3263	0.9005	0.9489
No log	11.7692	306	0.9061	0.3281	0.9061	0.9519
No log	11.8462	308	0.8791	0.2998	0.8791	0.9376
No log	11.9231	310	0.8487	0.4057	0.8487	0.9212
No log	12.0	312	0.8206	0.4701	0.8206	0.9059
No log	12.0769	314	0.8136	0.4701	0.8136	0.9020
No log	12.1538	316	0.8590	0.5317	0.8590	0.9268
No log	12.2308	318	0.8952	0.4893	0.8952	0.9462
No log	12.3077	320	0.8474	0.5317	0.8474	0.9206
No log	12.3846	322	0.8255	0.4142	0.8255	0.9086
No log	12.4615	324	0.8971	0.4754	0.8971	0.9471
No log	12.5385	326	0.9003	0.4754	0.9003	0.9489
No log	12.6154	328	0.8353	0.3596	0.8353	0.9139
No log	12.6923	330	0.8163	0.3629	0.8163	0.9035
No log	12.7692	332	0.8068	0.3629	0.8068	0.8982
No log	12.8462	334	0.8067	0.3994	0.8067	0.8982
No log	12.9231	336	0.7994	0.5368	0.7994	0.8941
No log	13.0	338	0.7858	0.5519	0.7858	0.8864
No log	13.0769	340	0.7688	0.5519	0.7688	0.8768
No log	13.1538	342	0.7496	0.5735	0.7496	0.8658
No log	13.2308	344	0.7561	0.5076	0.7561	0.8695
No log	13.3077	346	0.7708	0.5735	0.7708	0.8780
No log	13.3846	348	0.7995	0.5184	0.7995	0.8942
No log	13.4615	350	0.8066	0.4898	0.8066	0.8981
No log	13.5385	352	0.8146	0.4397	0.8146	0.9026
No log	13.6154	354	0.8256	0.4534	0.8256	0.9086
No log	13.6923	356	0.8302	0.4534	0.8302	0.9111
No log	13.7692	358	0.8323	0.3879	0.8323	0.9123
No log	13.8462	360	0.8302	0.3948	0.8302	0.9111
No log	13.9231	362	0.8187	0.4181	0.8187	0.9048
No log	14.0	364	0.7995	0.4847	0.7995	0.8942
No log	14.0769	366	0.7935	0.4847	0.7935	0.8908
No log	14.1538	368	0.7941	0.5194	0.7941	0.8911
No log	14.2308	370	0.8353	0.4425	0.8353	0.9139
No log	14.3077	372	0.8740	0.4201	0.8740	0.9349
No log	14.3846	374	0.9050	0.4258	0.9050	0.9513
No log	14.4615	376	0.9007	0.4258	0.9007	0.9490
No log	14.5385	378	0.9347	0.4351	0.9347	0.9668
No log	14.6154	380	0.9082	0.4351	0.9082	0.9530
No log	14.6923	382	0.8583	0.3926	0.8583	0.9264
No log	14.7692	384	0.8454	0.4568	0.8454	0.9195
No log	14.8462	386	0.8143	0.3948	0.8143	0.9024
No log	14.9231	388	0.8039	0.4555	0.8039	0.8966
No log	15.0	390	0.8074	0.4803	0.8074	0.8986
No log	15.0769	392	0.8071	0.4993	0.8071	0.8984
No log	15.1538	394	0.8343	0.4440	0.8343	0.9134
No log	15.2308	396	0.8669	0.4273	0.8669	0.9310
No log	15.3077	398	0.8952	0.4202	0.8952	0.9461
No log	15.3846	400	0.9105	0.4398	0.9105	0.9542
No log	15.4615	402	0.8977	0.4300	0.8977	0.9475
No log	15.5385	404	0.8713	0.4340	0.8713	0.9334
No log	15.6154	406	0.8505	0.4280	0.8505	0.9222
No log	15.6923	408	0.8698	0.4202	0.8698	0.9326
No log	15.7692	410	0.9150	0.4286	0.9150	0.9566
No log	15.8462	412	0.8786	0.4615	0.8786	0.9373
No log	15.9231	414	0.8527	0.4775	0.8527	0.9234
No log	16.0	416	0.8506	0.4568	0.8506	0.9223
No log	16.0769	418	0.8581	0.4202	0.8581	0.9263
No log	16.1538	420	0.8728	0.4631	0.8728	0.9342
No log	16.2308	422	0.8437	0.4425	0.8437	0.9185
No log	16.3077	424	0.8230	0.4277	0.8230	0.9072
No log	16.3846	426	0.8187	0.5027	0.8187	0.9048
No log	16.4615	428	0.8229	0.4898	0.8229	0.9071
No log	16.5385	430	0.8245	0.4965	0.8245	0.9080
No log	16.6154	432	0.8500	0.5114	0.8500	0.9220
No log	16.6923	434	0.8793	0.4869	0.8793	0.9377
No log	16.7692	436	0.8600	0.4881	0.8600	0.9274
No log	16.8462	438	0.8279	0.5287	0.8279	0.9099
No log	16.9231	440	0.8228	0.5287	0.8228	0.9071
No log	17.0	442	0.8596	0.4773	0.8596	0.9272
No log	17.0769	444	0.9565	0.4788	0.9565	0.9780
No log	17.1538	446	1.0177	0.4743	1.0177	1.0088
No log	17.2308	448	0.9480	0.4615	0.9480	0.9736
No log	17.3077	450	0.8537	0.4270	0.8537	0.9240
No log	17.3846	452	0.8308	0.4736	0.8308	0.9115
No log	17.4615	454	0.8461	0.4998	0.8461	0.9198
No log	17.5385	456	0.9260	0.4462	0.9260	0.9623
No log	17.6154	458	0.9711	0.4845	0.9711	0.9855
No log	17.6923	460	0.9228	0.4954	0.9228	0.9606
No log	17.7692	462	0.8438	0.4612	0.8438	0.9186
No log	17.8462	464	0.8000	0.4889	0.8000	0.8944
No log	17.9231	466	0.7952	0.5295	0.7952	0.8917
No log	18.0	468	0.7987	0.5142	0.7987	0.8937
No log	18.0769	470	0.7942	0.5324	0.7942	0.8912
No log	18.1538	472	0.7667	0.5435	0.7667	0.8756
No log	18.2308	474	0.7611	0.5458	0.7611	0.8724
No log	18.3077	476	0.7675	0.5435	0.7675	0.8761
No log	18.3846	478	0.7918	0.5275	0.7918	0.8898
No log	18.4615	480	0.8188	0.4812	0.8188	0.9049
No log	18.5385	482	0.8190	0.4812	0.8190	0.9050
No log	18.6154	484	0.7790	0.5458	0.7790	0.8826
No log	18.6923	486	0.7371	0.5413	0.7371	0.8586
No log	18.7692	488	0.7277	0.6002	0.7277	0.8531
No log	18.8462	490	0.7309	0.5885	0.7309	0.8549
No log	18.9231	492	0.7398	0.5773	0.7398	0.8601
No log	19.0	494	0.7699	0.5635	0.7699	0.8775
No log	19.0769	496	0.8397	0.5079	0.8397	0.9164
No log	19.1538	498	0.8693	0.5320	0.8693	0.9324
0.3427	19.2308	500	0.8454	0.5519	0.8454	0.9195
0.3427	19.3077	502	0.8105	0.4045	0.8105	0.9003
0.3427	19.3846	504	0.8252	0.3762	0.8252	0.9084
0.3427	19.4615	506	0.8257	0.3762	0.8257	0.9087
0.3427	19.5385	508	0.8314	0.5136	0.8314	0.9118
0.3427	19.6154	510	0.8523	0.5291	0.8523	0.9232

Framework versions

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