ArabicNewSplits6_FineTuningAraBERTFreeze_run1_AugV5_k2_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: 0.7995
• Qwk: 0.5018
• Mse: 0.7995
• Rmse: 0.8941

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	0.2857	2	6.2240	-0.0218	6.2240	2.4948
No log	0.5714	4	4.1337	-0.0204	4.1337	2.0331
No log	0.8571	6	2.9256	0.0083	2.9256	1.7104
No log	1.1429	8	2.1967	0.0730	2.1967	1.4821
No log	1.4286	10	1.5543	0.0879	1.5543	1.2467
No log	1.7143	12	1.0102	0.1327	1.0102	1.0051
No log	2.0	14	0.7588	0.1516	0.7588	0.8711
No log	2.2857	16	0.7695	0.1685	0.7695	0.8772
No log	2.5714	18	0.7714	0.0634	0.7714	0.8783
No log	2.8571	20	0.7620	0.1052	0.7620	0.8730
No log	3.1429	22	0.7086	0.2019	0.7086	0.8418
No log	3.4286	24	0.6798	0.2108	0.6798	0.8245
No log	3.7143	26	0.6592	0.3376	0.6592	0.8119
No log	4.0	28	0.6496	0.3824	0.6496	0.8060
No log	4.2857	30	0.6422	0.3506	0.6422	0.8014
No log	4.5714	32	0.6347	0.3506	0.6347	0.7967
No log	4.8571	34	0.6259	0.3629	0.6259	0.7912
No log	5.1429	36	0.6093	0.3506	0.6093	0.7806
No log	5.4286	38	0.5947	0.3558	0.5947	0.7712
No log	5.7143	40	0.5784	0.3981	0.5784	0.7605
No log	6.0	42	0.5609	0.4076	0.5609	0.7489
No log	6.2857	44	0.5504	0.4163	0.5504	0.7419
No log	6.5714	46	0.5405	0.4076	0.5405	0.7352
No log	6.8571	48	0.5312	0.3787	0.5312	0.7288
No log	7.1429	50	0.5270	0.3905	0.5270	0.7259
No log	7.4286	52	0.5317	0.4255	0.5317	0.7292
No log	7.7143	54	0.5539	0.4289	0.5539	0.7443
No log	8.0	56	0.5601	0.4506	0.5601	0.7484
No log	8.2857	58	0.5342	0.4560	0.5342	0.7309
No log	8.5714	60	0.5284	0.4630	0.5284	0.7269
No log	8.8571	62	0.5337	0.4203	0.5337	0.7306
No log	9.1429	64	0.5357	0.4670	0.5357	0.7319
No log	9.4286	66	0.5244	0.4153	0.5244	0.7242
No log	9.7143	68	0.5173	0.4428	0.5173	0.7192
No log	10.0	70	0.5084	0.4951	0.5084	0.7130
No log	10.2857	72	0.5112	0.4985	0.5112	0.7150
No log	10.5714	74	0.5220	0.5137	0.5220	0.7225
No log	10.8571	76	0.5236	0.5124	0.5236	0.7236
No log	11.1429	78	0.5306	0.4934	0.5306	0.7284
No log	11.4286	80	0.5524	0.4503	0.5524	0.7432
No log	11.7143	82	0.5563	0.4924	0.5563	0.7459
No log	12.0	84	0.5433	0.5215	0.5433	0.7371
No log	12.2857	86	0.5447	0.5429	0.5447	0.7380
No log	12.5714	88	0.5440	0.5535	0.5440	0.7376
No log	12.8571	90	0.5456	0.5836	0.5456	0.7386
No log	13.1429	92	0.5611	0.5811	0.5611	0.7491
No log	13.4286	94	0.5800	0.5733	0.5800	0.7616
No log	13.7143	96	0.5752	0.5865	0.5752	0.7584
No log	14.0	98	0.5737	0.6308	0.5737	0.7574
No log	14.2857	100	0.5810	0.5946	0.5810	0.7622
No log	14.5714	102	0.6158	0.5954	0.6158	0.7847
No log	14.8571	104	0.6326	0.5738	0.6326	0.7954
No log	15.1429	106	0.6287	0.5839	0.6287	0.7929
No log	15.4286	108	0.6162	0.5769	0.6162	0.7850
No log	15.7143	110	0.6178	0.5875	0.6178	0.7860
No log	16.0	112	0.6248	0.6014	0.6248	0.7905
No log	16.2857	114	0.6238	0.6043	0.6238	0.7898
No log	16.5714	116	0.6331	0.6043	0.6331	0.7957
No log	16.8571	118	0.6527	0.5814	0.6527	0.8079
No log	17.1429	120	0.6761	0.5446	0.6761	0.8222
No log	17.4286	122	0.6966	0.5296	0.6966	0.8347
No log	17.7143	124	0.6855	0.5390	0.6855	0.8280
No log	18.0	126	0.6638	0.5793	0.6638	0.8147
No log	18.2857	128	0.6457	0.6175	0.6457	0.8035
No log	18.5714	130	0.6448	0.6326	0.6448	0.8030
No log	18.8571	132	0.6533	0.6085	0.6533	0.8083
No log	19.1429	134	0.6621	0.5763	0.6621	0.8137
No log	19.4286	136	0.6551	0.5835	0.6551	0.8094
No log	19.7143	138	0.6657	0.6019	0.6657	0.8159
No log	20.0	140	0.6911	0.5478	0.6911	0.8313
No log	20.2857	142	0.7133	0.5462	0.7133	0.8446
No log	20.5714	144	0.7252	0.5380	0.7252	0.8516
No log	20.8571	146	0.7170	0.5464	0.7170	0.8468
No log	21.1429	148	0.7159	0.5371	0.7159	0.8461
No log	21.4286	150	0.7105	0.5631	0.7105	0.8429
No log	21.7143	152	0.7059	0.5913	0.7059	0.8402
No log	22.0	154	0.7063	0.5913	0.7063	0.8404
No log	22.2857	156	0.7043	0.5618	0.7043	0.8392
No log	22.5714	158	0.7058	0.5603	0.7058	0.8401
No log	22.8571	160	0.7059	0.5392	0.7059	0.8402
No log	23.1429	162	0.7169	0.5356	0.7169	0.8467
No log	23.4286	164	0.7160	0.5356	0.7160	0.8462
No log	23.7143	166	0.7191	0.5508	0.7191	0.8480
No log	24.0	168	0.7247	0.5412	0.7247	0.8513
No log	24.2857	170	0.7279	0.5412	0.7279	0.8531
No log	24.5714	172	0.7281	0.5480	0.7281	0.8533
No log	24.8571	174	0.7380	0.5480	0.7380	0.8591
No log	25.1429	176	0.7528	0.5480	0.7528	0.8676
No log	25.4286	178	0.7498	0.5410	0.7498	0.8659
No log	25.7143	180	0.7439	0.5356	0.7439	0.8625
No log	26.0	182	0.7564	0.5467	0.7564	0.8697
No log	26.2857	184	0.7733	0.5483	0.7733	0.8794
No log	26.5714	186	0.7863	0.5237	0.7863	0.8867
No log	26.8571	188	0.7858	0.5405	0.7858	0.8865
No log	27.1429	190	0.7711	0.5561	0.7711	0.8781
No log	27.4286	192	0.7723	0.5483	0.7723	0.8788
No log	27.7143	194	0.7750	0.5443	0.7750	0.8803
No log	28.0	196	0.7793	0.5365	0.7793	0.8828
No log	28.2857	198	0.7837	0.5018	0.7837	0.8853
No log	28.5714	200	0.7837	0.5010	0.7837	0.8852
No log	28.8571	202	0.7835	0.5266	0.7835	0.8852
No log	29.1429	204	0.7793	0.5454	0.7793	0.8828
No log	29.4286	206	0.7775	0.5351	0.7775	0.8818
No log	29.7143	208	0.7775	0.5351	0.7775	0.8818
No log	30.0	210	0.7750	0.5351	0.7750	0.8803
No log	30.2857	212	0.7814	0.5388	0.7814	0.8840
No log	30.5714	214	0.7918	0.5388	0.7918	0.8899
No log	30.8571	216	0.8026	0.5507	0.8026	0.8959
No log	31.1429	218	0.8013	0.5506	0.8013	0.8951
No log	31.4286	220	0.7905	0.5665	0.7905	0.8891
No log	31.7143	222	0.7946	0.5640	0.7946	0.8914
No log	32.0	224	0.8041	0.5334	0.8041	0.8967
No log	32.2857	226	0.8108	0.5282	0.8108	0.9004
No log	32.5714	228	0.8086	0.5374	0.8086	0.8992
No log	32.8571	230	0.7974	0.5348	0.7974	0.8930
No log	33.1429	232	0.7818	0.5497	0.7818	0.8842
No log	33.4286	234	0.7804	0.5339	0.7804	0.8834
No log	33.7143	236	0.7764	0.5328	0.7764	0.8811
No log	34.0	238	0.7789	0.5547	0.7789	0.8826
No log	34.2857	240	0.7963	0.5322	0.7963	0.8923
No log	34.5714	242	0.8171	0.5282	0.8171	0.9039
No log	34.8571	244	0.8034	0.5307	0.8034	0.8963
No log	35.1429	246	0.7804	0.5475	0.7804	0.8834
No log	35.4286	248	0.7731	0.5575	0.7731	0.8793
No log	35.7143	250	0.7708	0.5423	0.7708	0.8779
No log	36.0	252	0.7802	0.5171	0.7802	0.8833
No log	36.2857	254	0.8194	0.5270	0.8194	0.9052
No log	36.5714	256	0.8362	0.5261	0.8362	0.9145
No log	36.8571	258	0.8204	0.5149	0.8204	0.9058
No log	37.1429	260	0.8088	0.5189	0.8088	0.8993
No log	37.4286	262	0.8005	0.5388	0.8005	0.8947
No log	37.7143	264	0.7840	0.5278	0.7840	0.8854
No log	38.0	266	0.7771	0.5282	0.7771	0.8815
No log	38.2857	268	0.7869	0.5208	0.7869	0.8870
No log	38.5714	270	0.8106	0.5211	0.8106	0.9003
No log	38.8571	272	0.8123	0.5276	0.8123	0.9013
No log	39.1429	274	0.8061	0.5405	0.8061	0.8978
No log	39.4286	276	0.8106	0.5382	0.8106	0.9003
No log	39.7143	278	0.8004	0.5376	0.8004	0.8947
No log	40.0	280	0.7994	0.5376	0.7994	0.8941
No log	40.2857	282	0.8037	0.5365	0.8037	0.8965
No log	40.5714	284	0.8166	0.5171	0.8166	0.9037
No log	40.8571	286	0.8301	0.5255	0.8301	0.9111
No log	41.1429	288	0.8352	0.5276	0.8352	0.9139
No log	41.4286	290	0.8402	0.5151	0.8402	0.9166
No log	41.7143	292	0.8280	0.5259	0.8280	0.9099
No log	42.0	294	0.8105	0.5344	0.8105	0.9003
No log	42.2857	296	0.8064	0.5722	0.8064	0.8980
No log	42.5714	298	0.8071	0.5486	0.8071	0.8984
No log	42.8571	300	0.8159	0.5355	0.8159	0.9033
No log	43.1429	302	0.8322	0.5305	0.8322	0.9122
No log	43.4286	304	0.8609	0.5232	0.8609	0.9278
No log	43.7143	306	0.8574	0.5172	0.8574	0.9260
No log	44.0	308	0.8235	0.5211	0.8235	0.9075
No log	44.2857	310	0.7810	0.5405	0.7810	0.8837
No log	44.5714	312	0.7599	0.5629	0.7599	0.8717
No log	44.8571	314	0.7513	0.5838	0.7513	0.8668
No log	45.1429	316	0.7422	0.5511	0.7422	0.8615
No log	45.4286	318	0.7413	0.5508	0.7413	0.8610
No log	45.7143	320	0.7594	0.5311	0.7594	0.8714
No log	46.0	322	0.7772	0.5251	0.7772	0.8816
No log	46.2857	324	0.7838	0.5171	0.7838	0.8853
No log	46.5714	326	0.7972	0.5171	0.7972	0.8928
No log	46.8571	328	0.7994	0.5167	0.7994	0.8941
No log	47.1429	330	0.8048	0.5157	0.8048	0.8971
No log	47.4286	332	0.8009	0.5204	0.8009	0.8949
No log	47.7143	334	0.7965	0.5439	0.7965	0.8925
No log	48.0	336	0.7956	0.5315	0.7956	0.8920
No log	48.2857	338	0.7995	0.5315	0.7995	0.8942
No log	48.5714	340	0.8067	0.5784	0.8067	0.8982
No log	48.8571	342	0.8178	0.5289	0.8178	0.9043
No log	49.1429	344	0.8437	0.5233	0.8437	0.9185
No log	49.4286	346	0.8581	0.5136	0.8581	0.9264
No log	49.7143	348	0.8521	0.5050	0.8521	0.9231
No log	50.0	350	0.8392	0.5208	0.8392	0.9161
No log	50.2857	352	0.8216	0.54	0.8216	0.9064
No log	50.5714	354	0.8197	0.54	0.8197	0.9054
No log	50.8571	356	0.8277	0.5222	0.8277	0.9098
No log	51.1429	358	0.8371	0.5596	0.8371	0.9149
No log	51.4286	360	0.8554	0.5283	0.8554	0.9249
No log	51.7143	362	0.8691	0.5279	0.8691	0.9323
No log	52.0	364	0.8769	0.5279	0.8769	0.9364
No log	52.2857	366	0.8895	0.5371	0.8895	0.9432
No log	52.5714	368	0.8785	0.5558	0.8785	0.9373
No log	52.8571	370	0.8454	0.5547	0.8454	0.9194
No log	53.1429	372	0.8323	0.5441	0.8323	0.9123
No log	53.4286	374	0.8323	0.5548	0.8323	0.9123
No log	53.7143	376	0.8303	0.5669	0.8303	0.9112
No log	54.0	378	0.8279	0.5696	0.8279	0.9099
No log	54.2857	380	0.8264	0.5697	0.8264	0.9091
No log	54.5714	382	0.8287	0.5523	0.8287	0.9103
No log	54.8571	384	0.8371	0.5243	0.8371	0.9149
No log	55.1429	386	0.8504	0.5620	0.8504	0.9222
No log	55.4286	388	0.8395	0.5633	0.8395	0.9163
No log	55.7143	390	0.8111	0.5288	0.8111	0.9006
No log	56.0	392	0.7896	0.5154	0.7896	0.8886
No log	56.2857	394	0.7777	0.5240	0.7777	0.8819
No log	56.5714	396	0.7778	0.5536	0.7778	0.8819
No log	56.8571	398	0.7854	0.5677	0.7854	0.8862
No log	57.1429	400	0.7928	0.5510	0.7928	0.8904
No log	57.4286	402	0.7975	0.5548	0.7975	0.8930
No log	57.7143	404	0.7955	0.5549	0.7955	0.8919
No log	58.0	406	0.7965	0.5498	0.7965	0.8925
No log	58.2857	408	0.8045	0.5637	0.8045	0.8969
No log	58.5714	410	0.8114	0.5469	0.8114	0.9008
No log	58.8571	412	0.8078	0.5481	0.8078	0.8988
No log	59.1429	414	0.7989	0.5391	0.7989	0.8938
No log	59.4286	416	0.7879	0.5292	0.7879	0.8877
No log	59.7143	418	0.7764	0.5432	0.7764	0.8811
No log	60.0	420	0.7708	0.5432	0.7708	0.8779
No log	60.2857	422	0.7706	0.5391	0.7706	0.8779
No log	60.5714	424	0.7803	0.5547	0.7803	0.8833
No log	60.8571	426	0.8036	0.5428	0.8036	0.8964
No log	61.1429	428	0.8194	0.5467	0.8194	0.9052
No log	61.4286	430	0.8306	0.5414	0.8306	0.9114
No log	61.7143	432	0.8392	0.5337	0.8392	0.9161
No log	62.0	434	0.8399	0.5414	0.8399	0.9165
No log	62.2857	436	0.8409	0.5414	0.8409	0.9170
No log	62.5714	438	0.8308	0.5274	0.8308	0.9115
No log	62.8571	440	0.8173	0.5522	0.8173	0.9040
No log	63.1429	442	0.8115	0.5266	0.8115	0.9008
No log	63.4286	444	0.8130	0.5092	0.8130	0.9017
No log	63.7143	446	0.8226	0.5256	0.8226	0.9070
No log	64.0	448	0.8371	0.5509	0.8371	0.9149
No log	64.2857	450	0.8556	0.5432	0.8556	0.9250
No log	64.5714	452	0.8738	0.5263	0.8738	0.9348
No log	64.8571	454	0.8768	0.5259	0.8768	0.9364
No log	65.1429	456	0.8657	0.5239	0.8657	0.9304
No log	65.4286	458	0.8422	0.5208	0.8422	0.9177
No log	65.7143	460	0.8301	0.5339	0.8301	0.9111
No log	66.0	462	0.8258	0.5509	0.8258	0.9087
No log	66.2857	464	0.8193	0.5509	0.8193	0.9052
No log	66.5714	466	0.8100	0.5409	0.8100	0.9000
No log	66.8571	468	0.8025	0.5042	0.8025	0.8958
No log	67.1429	470	0.8007	0.4741	0.8007	0.8948
No log	67.4286	472	0.8024	0.4860	0.8024	0.8958
No log	67.7143	474	0.8096	0.4714	0.8096	0.8998
No log	68.0	476	0.8172	0.4826	0.8172	0.9040
No log	68.2857	478	0.8302	0.5127	0.8302	0.9112
No log	68.5714	480	0.8526	0.5633	0.8526	0.9234
No log	68.8571	482	0.8631	0.5620	0.8631	0.9290
No log	69.1429	484	0.8545	0.5473	0.8545	0.9244
No log	69.4286	486	0.8348	0.5482	0.8348	0.9137
No log	69.7143	488	0.8211	0.5446	0.8211	0.9061
No log	70.0	490	0.8169	0.5500	0.8169	0.9038
No log	70.2857	492	0.8156	0.5437	0.8156	0.9031
No log	70.5714	494	0.8144	0.5409	0.8144	0.9025
No log	70.8571	496	0.8218	0.5548	0.8218	0.9065
No log	71.1429	498	0.8289	0.5485	0.8289	0.9104
0.4687	71.4286	500	0.8278	0.5474	0.8278	0.9098
0.4687	71.7143	502	0.8211	0.5327	0.8211	0.9061
0.4687	72.0	504	0.8169	0.4920	0.8169	0.9038
0.4687	72.2857	506	0.8154	0.4911	0.8154	0.9030
0.4687	72.5714	508	0.8162	0.4911	0.8162	0.9034
0.4687	72.8571	510	0.8215	0.5633	0.8215	0.9063
0.4687	73.1429	512	0.8232	0.5633	0.8232	0.9073
0.4687	73.4286	514	0.8292	0.5634	0.8292	0.9106
0.4687	73.7143	516	0.8292	0.5634	0.8292	0.9106
0.4687	74.0	518	0.8203	0.5521	0.8203	0.9057
0.4687	74.2857	520	0.8075	0.5457	0.8075	0.8986
0.4687	74.5714	522	0.7970	0.5421	0.7970	0.8927
0.4687	74.8571	524	0.7943	0.5184	0.7943	0.8913
0.4687	75.1429	526	0.7952	0.4995	0.7952	0.8917
0.4687	75.4286	528	0.7995	0.5018	0.7995	0.8941

Framework versions

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