ArabicNewSplits6_FineTuningAraBERT_run2_AugV5_k5_task5_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: 0.7588
• Qwk: 0.7004
• Mse: 0.7588
• Rmse: 0.8711

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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	0.1	2	2.3515	-0.0201	2.3515	1.5334
No log	0.2	4	1.5743	0.1804	1.5743	1.2547
No log	0.3	6	1.4911	0.0962	1.4911	1.2211
No log	0.4	8	1.5553	0.1955	1.5553	1.2471
No log	0.5	10	1.6274	0.3369	1.6274	1.2757
No log	0.6	12	1.4857	0.1276	1.4857	1.2189
No log	0.7	14	1.4648	0.1009	1.4648	1.2103
No log	0.8	16	1.4577	0.0811	1.4577	1.2074
No log	0.9	18	1.4115	0.1057	1.4115	1.1881
No log	1.0	20	1.4379	0.0859	1.4379	1.1991
No log	1.1	22	1.5012	0.2174	1.5012	1.2252
No log	1.2	24	1.5528	0.2731	1.5528	1.2461
No log	1.3	26	1.6686	0.3214	1.6686	1.2917
No log	1.4	28	1.8822	0.2788	1.8822	1.3719
No log	1.5	30	1.8667	0.2934	1.8667	1.3663
No log	1.6	32	1.6847	0.3642	1.6847	1.2980
No log	1.7	34	1.4215	0.4073	1.4215	1.1923
No log	1.8	36	1.2429	0.2717	1.2429	1.1148
No log	1.9	38	1.1813	0.2389	1.1813	1.0869
No log	2.0	40	1.1926	0.2452	1.1926	1.0920
No log	2.1	42	1.1651	0.2718	1.1651	1.0794
No log	2.2	44	1.1074	0.3281	1.1074	1.0523
No log	2.3	46	1.1226	0.4217	1.1226	1.0595
No log	2.4	48	1.2471	0.4149	1.2471	1.1167
No log	2.5	50	1.2194	0.4286	1.2194	1.1042
No log	2.6	52	1.1923	0.4073	1.1923	1.0919
No log	2.7	54	1.3077	0.4128	1.3077	1.1436
No log	2.8	56	1.3472	0.3891	1.3472	1.1607
No log	2.9	58	1.3315	0.4126	1.3315	1.1539
No log	3.0	60	1.1433	0.4032	1.1433	1.0693
No log	3.1	62	1.0340	0.4439	1.0340	1.0168
No log	3.2	64	1.0286	0.4327	1.0286	1.0142
No log	3.3	66	1.0400	0.4574	1.0400	1.0198
No log	3.4	68	1.0216	0.4730	1.0216	1.0107
No log	3.5	70	0.9581	0.5057	0.9581	0.9788
No log	3.6	72	1.0332	0.4856	1.0332	1.0165
No log	3.7	74	1.3527	0.4817	1.3527	1.1631
No log	3.8	76	1.5324	0.4636	1.5324	1.2379
No log	3.9	78	1.5564	0.4596	1.5564	1.2476
No log	4.0	80	1.3033	0.4817	1.3033	1.1416
No log	4.1	82	1.0266	0.5126	1.0266	1.0132
No log	4.2	84	0.9423	0.5172	0.9423	0.9707
No log	4.3	86	0.9304	0.5398	0.9304	0.9646
No log	4.4	88	0.9557	0.5490	0.9557	0.9776
No log	4.5	90	0.9740	0.5425	0.9740	0.9869
No log	4.6	92	1.0209	0.5455	1.0209	1.0104
No log	4.7	94	1.1036	0.5256	1.1036	1.0505
No log	4.8	96	1.0424	0.5374	1.0424	1.0210
No log	4.9	98	0.9124	0.6298	0.9124	0.9552
No log	5.0	100	0.8661	0.6385	0.8661	0.9306
No log	5.1	102	0.8333	0.6469	0.8333	0.9129
No log	5.2	104	0.8442	0.6451	0.8442	0.9188
No log	5.3	106	0.9257	0.6301	0.9257	0.9621
No log	5.4	108	1.0467	0.6099	1.0467	1.0231
No log	5.5	110	0.9822	0.6300	0.9822	0.9911
No log	5.6	112	0.9660	0.6286	0.9660	0.9828
No log	5.7	114	0.8785	0.6523	0.8785	0.9373
No log	5.8	116	0.7643	0.6827	0.7643	0.8742
No log	5.9	118	0.7212	0.6999	0.7212	0.8492
No log	6.0	120	0.7327	0.6985	0.7327	0.8560
No log	6.1	122	0.8022	0.6622	0.8022	0.8956
No log	6.2	124	0.9035	0.6282	0.9035	0.9505
No log	6.3	126	1.0753	0.5703	1.0753	1.0370
No log	6.4	128	1.1506	0.5641	1.1506	1.0727
No log	6.5	130	1.0722	0.5714	1.0722	1.0355
No log	6.6	132	0.9181	0.6298	0.9181	0.9582
No log	6.7	134	0.8269	0.6264	0.8269	0.9093
No log	6.8	136	0.7880	0.6656	0.7880	0.8877
No log	6.9	138	0.7953	0.6667	0.7953	0.8918
No log	7.0	140	0.8240	0.6447	0.8240	0.9077
No log	7.1	142	0.8631	0.6459	0.8631	0.9291
No log	7.2	144	0.8408	0.6531	0.8408	0.9169
No log	7.3	146	0.8036	0.6659	0.8036	0.8964
No log	7.4	148	0.8183	0.6632	0.8183	0.9046
No log	7.5	150	0.8124	0.6613	0.8124	0.9013
No log	7.6	152	0.8293	0.6742	0.8293	0.9107
No log	7.7	154	0.8371	0.6679	0.8371	0.9149
No log	7.8	156	0.8110	0.6734	0.8110	0.9005
No log	7.9	158	0.7885	0.6781	0.7885	0.8880
No log	8.0	160	0.7880	0.6781	0.7880	0.8877
No log	8.1	162	0.7689	0.6762	0.7689	0.8769
No log	8.2	164	0.7546	0.6914	0.7546	0.8687
No log	8.3	166	0.7296	0.7224	0.7296	0.8542
No log	8.4	168	0.7191	0.7207	0.7191	0.8480
No log	8.5	170	0.7092	0.7262	0.7092	0.8422
No log	8.6	172	0.6987	0.7310	0.6987	0.8359
No log	8.7	174	0.6963	0.7310	0.6963	0.8344
No log	8.8	176	0.6995	0.7222	0.6995	0.8364
No log	8.9	178	0.7148	0.7188	0.7148	0.8454
No log	9.0	180	0.7417	0.7180	0.7417	0.8612
No log	9.1	182	0.7664	0.7033	0.7664	0.8754
No log	9.2	184	0.7825	0.6923	0.7825	0.8846
No log	9.3	186	0.7932	0.6878	0.7932	0.8906
No log	9.4	188	0.7932	0.6878	0.7932	0.8906
No log	9.5	190	0.7877	0.6860	0.7877	0.8875
No log	9.6	192	0.7779	0.6906	0.7779	0.8820
No log	9.7	194	0.7690	0.6906	0.7690	0.8769
No log	9.8	196	0.7623	0.7004	0.7623	0.8731
No log	9.9	198	0.7594	0.7004	0.7594	0.8714
No log	10.0	200	0.7588	0.7004	0.7588	0.8711

Framework versions

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