ArabicNewSplits6_FineTuningAraBERTFreeze_run3_AugV5_k14_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: 0.8796
• Qwk: 0.3922
• Mse: 0.8796
• Rmse: 0.9379

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	0.0556	2	6.4552	-0.0278	6.4552	2.5407
No log	0.1111	4	4.2993	-0.0299	4.2993	2.0735
No log	0.1667	6	2.9570	-0.0006	2.9570	1.7196
No log	0.2222	8	2.0770	-0.0004	2.0770	1.4412
No log	0.2778	10	1.5844	-0.0270	1.5844	1.2587
No log	0.3333	12	1.6218	-0.0702	1.6218	1.2735
No log	0.3889	14	1.6099	-0.0729	1.6099	1.2688
No log	0.4444	16	1.3686	-0.0435	1.3686	1.1699
No log	0.5	18	1.1662	-0.0092	1.1662	1.0799
No log	0.5556	20	1.1061	0.1026	1.1061	1.0517
No log	0.6111	22	0.9968	0.0939	0.9968	0.9984
No log	0.6667	24	0.8775	0.0947	0.8775	0.9367
No log	0.7222	26	0.8300	0.1555	0.8300	0.9111
No log	0.7778	28	0.8342	0.1625	0.8342	0.9134
No log	0.8333	30	0.9095	0.1756	0.9095	0.9537
No log	0.8889	32	0.9372	0.1792	0.9372	0.9681
No log	0.9444	34	0.9725	0.1555	0.9725	0.9862
No log	1.0	36	1.0925	0.1770	1.0925	1.0452
No log	1.0556	38	1.1913	0.2109	1.1913	1.0914
No log	1.1111	40	1.2005	0.2109	1.2005	1.0957
No log	1.1667	42	1.1179	0.2267	1.1179	1.0573
No log	1.2222	44	0.9713	0.2114	0.9713	0.9856
No log	1.2778	46	0.8647	0.3231	0.8647	0.9299
No log	1.3333	48	0.9032	0.2836	0.9032	0.9504
No log	1.3889	50	1.1247	0.2433	1.1247	1.0605
No log	1.4444	52	1.3871	0.1664	1.3871	1.1778
No log	1.5	54	1.2415	0.2368	1.2415	1.1142
No log	1.5556	56	0.9731	0.2901	0.9731	0.9865
No log	1.6111	58	0.7757	0.3359	0.7757	0.8808
No log	1.6667	60	0.7635	0.3730	0.7635	0.8738
No log	1.7222	62	0.8001	0.3629	0.8001	0.8945
No log	1.7778	64	0.8365	0.2854	0.8365	0.9146
No log	1.8333	66	0.8735	0.2921	0.8735	0.9346
No log	1.8889	68	0.8445	0.2867	0.8445	0.9190
No log	1.9444	70	0.7159	0.3661	0.7159	0.8461
No log	2.0	72	0.6471	0.4318	0.6471	0.8044
No log	2.0556	74	0.6285	0.4555	0.6285	0.7928
No log	2.1111	76	0.6252	0.4672	0.6252	0.7907
No log	2.1667	78	0.6434	0.4781	0.6434	0.8021
No log	2.2222	80	0.6822	0.4038	0.6822	0.8259
No log	2.2778	82	0.8241	0.3679	0.8241	0.9078
No log	2.3333	84	0.9463	0.3398	0.9463	0.9728
No log	2.3889	86	0.8844	0.3645	0.8844	0.9404
No log	2.4444	88	0.7420	0.3737	0.7420	0.8614
No log	2.5	90	0.6760	0.4270	0.6760	0.8222
No log	2.5556	92	0.6651	0.4105	0.6651	0.8156
No log	2.6111	94	0.6438	0.4388	0.6438	0.8024
No log	2.6667	96	0.6311	0.4528	0.6311	0.7944
No log	2.7222	98	0.6455	0.4497	0.6455	0.8034
No log	2.7778	100	0.6394	0.4951	0.6394	0.7997
No log	2.8333	102	0.6219	0.5010	0.6219	0.7886
No log	2.8889	104	0.6048	0.4921	0.6048	0.7777
No log	2.9444	106	0.5758	0.4930	0.5758	0.7588
No log	3.0	108	0.5858	0.4813	0.5858	0.7654
No log	3.0556	110	0.5714	0.4869	0.5714	0.7559
No log	3.1111	112	0.5785	0.4493	0.5785	0.7606
No log	3.1667	114	0.6021	0.4873	0.6021	0.7760
No log	3.2222	116	0.6102	0.4816	0.6102	0.7812
No log	3.2778	118	0.6660	0.4698	0.6660	0.8161
No log	3.3333	120	0.7917	0.4518	0.7917	0.8898
No log	3.3889	122	0.9038	0.4497	0.9038	0.9507
No log	3.4444	124	0.8021	0.4592	0.8021	0.8956
No log	3.5	126	0.6823	0.4744	0.6823	0.8260
No log	3.5556	128	0.5955	0.5318	0.5955	0.7717
No log	3.6111	130	0.5801	0.5171	0.5801	0.7616
No log	3.6667	132	0.5975	0.5366	0.5975	0.7730
No log	3.7222	134	0.6280	0.5541	0.6280	0.7925
No log	3.7778	136	0.7137	0.4988	0.7137	0.8448
No log	3.8333	138	0.8394	0.4739	0.8394	0.9162
No log	3.8889	140	0.8066	0.4787	0.8066	0.8981
No log	3.9444	142	0.7452	0.4639	0.7452	0.8632
No log	4.0	144	0.7024	0.4947	0.7024	0.8381
No log	4.0556	146	0.6524	0.5172	0.6524	0.8077
No log	4.1111	148	0.6155	0.5605	0.6155	0.7845
No log	4.1667	150	0.6512	0.5471	0.6512	0.8069
No log	4.2222	152	0.7499	0.4168	0.7499	0.8660
No log	4.2778	154	0.8532	0.4509	0.8532	0.9237
No log	4.3333	156	0.7958	0.4538	0.7958	0.8921
No log	4.3889	158	0.7231	0.4864	0.7231	0.8503
No log	4.4444	160	0.6434	0.5469	0.6434	0.8021
No log	4.5	162	0.6271	0.5476	0.6271	0.7919
No log	4.5556	164	0.5982	0.5441	0.5982	0.7734
No log	4.6111	166	0.5960	0.5490	0.5960	0.7720
No log	4.6667	168	0.6102	0.5585	0.6102	0.7812
No log	4.7222	170	0.6203	0.5253	0.6203	0.7876
No log	4.7778	172	0.6277	0.5287	0.6277	0.7923
No log	4.8333	174	0.6251	0.5626	0.6251	0.7906
No log	4.8889	176	0.6879	0.5362	0.6879	0.8294
No log	4.9444	178	0.8217	0.4797	0.8217	0.9065
No log	5.0	180	0.8523	0.4633	0.8523	0.9232
No log	5.0556	182	0.7717	0.4952	0.7717	0.8784
No log	5.1111	184	0.7022	0.5149	0.7022	0.8380
No log	5.1667	186	0.6885	0.5073	0.6885	0.8298
No log	5.2222	188	0.6868	0.5060	0.6868	0.8288
No log	5.2778	190	0.7148	0.5131	0.7148	0.8455
No log	5.3333	192	0.7248	0.4779	0.7248	0.8513
No log	5.3889	194	0.7172	0.5032	0.7172	0.8468
No log	5.4444	196	0.7266	0.4840	0.7266	0.8524
No log	5.5	198	0.6975	0.4955	0.6975	0.8352
No log	5.5556	200	0.7036	0.5033	0.7036	0.8388
No log	5.6111	202	0.7372	0.4714	0.7372	0.8586
No log	5.6667	204	0.6939	0.4588	0.6939	0.8330
No log	5.7222	206	0.6535	0.4789	0.6535	0.8084
No log	5.7778	208	0.6519	0.5308	0.6519	0.8074
No log	5.8333	210	0.6370	0.5181	0.6370	0.7982
No log	5.8889	212	0.6385	0.4951	0.6385	0.7991
No log	5.9444	214	0.7034	0.5603	0.7034	0.8387
No log	6.0	216	0.8612	0.4797	0.8612	0.9280
No log	6.0556	218	0.9767	0.4095	0.9767	0.9883
No log	6.1111	220	0.9529	0.4315	0.9529	0.9761
No log	6.1667	222	0.8340	0.4707	0.8340	0.9132
No log	6.2222	224	0.7544	0.5032	0.7544	0.8685
No log	6.2778	226	0.7466	0.5088	0.7466	0.8641
No log	6.3333	228	0.7604	0.5071	0.7604	0.8720
No log	6.3889	230	0.7960	0.4674	0.7960	0.8922
No log	6.4444	232	0.8309	0.4563	0.8309	0.9115
No log	6.5	234	0.7856	0.4773	0.7856	0.8864
No log	6.5556	236	0.7408	0.5068	0.7408	0.8607
No log	6.6111	238	0.6855	0.5068	0.6855	0.8279
No log	6.6667	240	0.6655	0.4760	0.6655	0.8158
No log	6.7222	242	0.6969	0.5026	0.6969	0.8348
No log	6.7778	244	0.7275	0.4731	0.7275	0.8529
No log	6.8333	246	0.7683	0.4713	0.7683	0.8765
No log	6.8889	248	0.7831	0.4799	0.7831	0.8849
No log	6.9444	250	0.8226	0.4779	0.8226	0.9070
No log	7.0	252	0.8736	0.4498	0.8736	0.9347
No log	7.0556	254	0.8813	0.4377	0.8813	0.9388
No log	7.1111	256	0.8036	0.4765	0.8036	0.8964
No log	7.1667	258	0.7702	0.4591	0.7702	0.8776
No log	7.2222	260	0.7730	0.4591	0.7730	0.8792
No log	7.2778	262	0.7768	0.4734	0.7768	0.8814
No log	7.3333	264	0.7961	0.4823	0.7961	0.8922
No log	7.3889	266	0.8352	0.4629	0.8352	0.9139
No log	7.4444	268	0.8375	0.4672	0.8375	0.9152
No log	7.5	270	0.8303	0.4659	0.8303	0.9112
No log	7.5556	272	0.8545	0.4404	0.8545	0.9244
No log	7.6111	274	0.8829	0.4323	0.8829	0.9397
No log	7.6667	276	0.8456	0.4558	0.8456	0.9196
No log	7.7222	278	0.8520	0.4338	0.8520	0.9230
No log	7.7778	280	0.8066	0.4646	0.8066	0.8981
No log	7.8333	282	0.7844	0.4668	0.7844	0.8857
No log	7.8889	284	0.8089	0.4600	0.8089	0.8994
No log	7.9444	286	0.8193	0.4411	0.8193	0.9052
No log	8.0	288	0.7667	0.4708	0.7667	0.8756
No log	8.0556	290	0.7180	0.4642	0.7180	0.8473
No log	8.1111	292	0.7040	0.4359	0.7040	0.8390
No log	8.1667	294	0.7030	0.4494	0.7030	0.8384
No log	8.2222	296	0.7073	0.4278	0.7073	0.8410
No log	8.2778	298	0.7317	0.4964	0.7317	0.8554
No log	8.3333	300	0.7968	0.4962	0.7968	0.8926
No log	8.3889	302	0.8570	0.4837	0.8570	0.9257
No log	8.4444	304	0.8373	0.4805	0.8373	0.9150
No log	8.5	306	0.8293	0.5040	0.8293	0.9107
No log	8.5556	308	0.8366	0.5010	0.8366	0.9147
No log	8.6111	310	0.8477	0.4937	0.8477	0.9207
No log	8.6667	312	0.8612	0.4815	0.8612	0.9280
No log	8.7222	314	0.8759	0.4651	0.8759	0.9359
No log	8.7778	316	0.8761	0.4735	0.8761	0.9360
No log	8.8333	318	0.7966	0.4494	0.7966	0.8925
No log	8.8889	320	0.7541	0.4543	0.7541	0.8684
No log	8.9444	322	0.7344	0.4296	0.7344	0.8570
No log	9.0	324	0.7461	0.4638	0.7461	0.8638
No log	9.0556	326	0.7662	0.4475	0.7662	0.8753
No log	9.1111	328	0.7927	0.4759	0.7927	0.8903
No log	9.1667	330	0.7996	0.4673	0.7996	0.8942
No log	9.2222	332	0.8017	0.4713	0.8017	0.8954
No log	9.2778	334	0.8368	0.4536	0.8368	0.9148
No log	9.3333	336	0.9037	0.4202	0.9037	0.9506
No log	9.3889	338	0.8989	0.4222	0.8989	0.9481
No log	9.4444	340	0.8864	0.4275	0.8864	0.9415
No log	9.5	342	0.8167	0.4285	0.8167	0.9037
No log	9.5556	344	0.7772	0.4336	0.7772	0.8816
No log	9.6111	346	0.7706	0.4194	0.7706	0.8779
No log	9.6667	348	0.7778	0.4269	0.7778	0.8820
No log	9.7222	350	0.7571	0.4355	0.7571	0.8701
No log	9.7778	352	0.7390	0.4354	0.7390	0.8596
No log	9.8333	354	0.7498	0.4624	0.7498	0.8659
No log	9.8889	356	0.7559	0.4624	0.7559	0.8694
No log	9.9444	358	0.7678	0.4619	0.7678	0.8763
No log	10.0	360	0.7665	0.4642	0.7665	0.8755
No log	10.0556	362	0.7801	0.4420	0.7801	0.8833
No log	10.1111	364	0.7936	0.4265	0.7936	0.8909
No log	10.1667	366	0.8062	0.4265	0.8062	0.8979
No log	10.2222	368	0.7891	0.4637	0.7891	0.8883
No log	10.2778	370	0.7830	0.4770	0.7830	0.8849
No log	10.3333	372	0.7986	0.4748	0.7986	0.8937
No log	10.3889	374	0.8240	0.4714	0.8240	0.9077
No log	10.4444	376	0.8331	0.4475	0.8331	0.9128
No log	10.5	378	0.8470	0.4533	0.8470	0.9203
No log	10.5556	380	0.9163	0.4425	0.9163	0.9572
No log	10.6111	382	0.9407	0.4122	0.9407	0.9699
No log	10.6667	384	0.8550	0.4305	0.8550	0.9246
No log	10.7222	386	0.8005	0.4610	0.8005	0.8947
No log	10.7778	388	0.8298	0.4882	0.8298	0.9110
No log	10.8333	390	0.8284	0.5	0.8284	0.9102
No log	10.8889	392	0.7716	0.5238	0.7716	0.8784
No log	10.9444	394	0.7549	0.5014	0.7549	0.8689
No log	11.0	396	0.7745	0.4729	0.7745	0.8801
No log	11.0556	398	0.8137	0.4588	0.8137	0.9020
No log	11.1111	400	0.8456	0.4311	0.8456	0.9196
No log	11.1667	402	0.8775	0.4134	0.8775	0.9368
No log	11.2222	404	0.9391	0.3916	0.9391	0.9691
No log	11.2778	406	0.9463	0.4066	0.9463	0.9728
No log	11.3333	408	0.9280	0.4168	0.9280	0.9633
No log	11.3889	410	0.9436	0.4222	0.9436	0.9714
No log	11.4444	412	0.9632	0.4256	0.9632	0.9814
No log	11.5	414	0.9199	0.4410	0.9199	0.9591
No log	11.5556	416	0.9054	0.4347	0.9054	0.9515
No log	11.6111	418	0.9115	0.4277	0.9115	0.9547
No log	11.6667	420	0.9292	0.4141	0.9292	0.9640
No log	11.7222	422	0.9463	0.4022	0.9463	0.9728
No log	11.7778	424	0.9564	0.4192	0.9564	0.9779
No log	11.8333	426	0.9183	0.4110	0.9183	0.9583
No log	11.8889	428	0.8673	0.4151	0.8673	0.9313
No log	11.9444	430	0.8423	0.4204	0.8423	0.9178
No log	12.0	432	0.8253	0.4280	0.8253	0.9084
No log	12.0556	434	0.8084	0.4447	0.8084	0.8991
No log	12.1111	436	0.7985	0.4430	0.7985	0.8936
No log	12.1667	438	0.8160	0.4358	0.8160	0.9033
No log	12.2222	440	0.8286	0.4160	0.8286	0.9103
No log	12.2778	442	0.8346	0.4069	0.8346	0.9136
No log	12.3333	444	0.8432	0.4228	0.8432	0.9182
No log	12.3889	446	0.8691	0.4011	0.8691	0.9323
No log	12.4444	448	0.8745	0.3875	0.8745	0.9351
No log	12.5	450	0.8286	0.4209	0.8286	0.9103
No log	12.5556	452	0.7936	0.4368	0.7936	0.8908
No log	12.6111	454	0.7860	0.4384	0.7860	0.8866
No log	12.6667	456	0.7850	0.4329	0.7850	0.8860
No log	12.7222	458	0.7973	0.4512	0.7973	0.8929
No log	12.7778	460	0.8016	0.4384	0.8016	0.8953
No log	12.8333	462	0.8067	0.4662	0.8067	0.8982
No log	12.8889	464	0.8229	0.4370	0.8229	0.9071
No log	12.9444	466	0.8527	0.4125	0.8527	0.9234
No log	13.0	468	0.8564	0.4060	0.8564	0.9254
No log	13.0556	470	0.8857	0.4042	0.8857	0.9411
No log	13.1111	472	0.8886	0.4164	0.8886	0.9426
No log	13.1667	474	0.8219	0.4012	0.8219	0.9066
No log	13.2222	476	0.7910	0.4411	0.7910	0.8894
No log	13.2778	478	0.7984	0.4317	0.7984	0.8936
No log	13.3333	480	0.8065	0.4164	0.8065	0.8981
No log	13.3889	482	0.8183	0.4359	0.8183	0.9046
No log	13.4444	484	0.8390	0.3927	0.8390	0.9160
No log	13.5	486	0.8548	0.3883	0.8548	0.9245
No log	13.5556	488	0.8126	0.4635	0.8126	0.9014
No log	13.6111	490	0.7881	0.4657	0.7881	0.8878
No log	13.6667	492	0.7941	0.4596	0.7941	0.8912
No log	13.7222	494	0.8164	0.4662	0.8164	0.9036
No log	13.7778	496	0.8333	0.4489	0.8333	0.9129
No log	13.8333	498	0.8497	0.4368	0.8497	0.9218
0.5645	13.8889	500	0.8584	0.4489	0.8584	0.9265
0.5645	13.9444	502	0.8661	0.4605	0.8661	0.9306
0.5645	14.0	504	0.8890	0.4716	0.8890	0.9429
0.5645	14.0556	506	0.8915	0.4588	0.8915	0.9442
0.5645	14.1111	508	0.8746	0.4825	0.8746	0.9352
0.5645	14.1667	510	0.8757	0.4647	0.8757	0.9358
0.5645	14.2222	512	0.8871	0.4463	0.8871	0.9419
0.5645	14.2778	514	0.8727	0.4446	0.8727	0.9342
0.5645	14.3333	516	0.8589	0.4556	0.8589	0.9268
0.5645	14.3889	518	0.8549	0.4542	0.8549	0.9246
0.5645	14.4444	520	0.8348	0.4419	0.8348	0.9137
0.5645	14.5	522	0.8248	0.4279	0.8248	0.9082
0.5645	14.5556	524	0.8339	0.4316	0.8339	0.9132
0.5645	14.6111	526	0.8693	0.3980	0.8693	0.9323
0.5645	14.6667	528	0.8796	0.3922	0.8796	0.9379

Framework versions

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