arabert_augmented_only_k1_organization_task1_fold0

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: 1.2195
• Qwk: 0.2338
• Mse: 1.2195
• Rmse: 1.1043

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	0.1818	2	5.1319	0.0120	5.1319	2.2654
No log	0.3636	4	2.8711	0.0834	2.8711	1.6944
No log	0.5455	6	1.6254	0.2921	1.6254	1.2749
No log	0.7273	8	1.4862	0.2292	1.4862	1.2191
No log	0.9091	10	1.3610	0.2380	1.3610	1.1666
No log	1.0909	12	1.0187	0.3383	1.0187	1.0093
No log	1.2727	14	0.9818	0.3383	0.9818	0.9908
No log	1.4545	16	0.9889	0.2687	0.9889	0.9945
No log	1.6364	18	1.1062	0.3173	1.1062	1.0518
No log	1.8182	20	1.3022	0.2463	1.3022	1.1411
No log	2.0	22	1.2435	0.2607	1.2435	1.1151
No log	2.1818	24	1.1962	0.2786	1.1962	1.0937
No log	2.3636	26	1.3167	0.1414	1.3167	1.1475
No log	2.5455	28	1.5147	0.1414	1.5147	1.2307
No log	2.7273	30	1.6231	0.2025	1.6231	1.2740
No log	2.9091	32	1.7717	0.0753	1.7717	1.3311
No log	3.0909	34	1.9347	-0.0328	1.9347	1.3909
No log	3.2727	36	1.9932	0.0106	1.9932	1.4118
No log	3.4545	38	1.9113	0.0533	1.9113	1.3825
No log	3.6364	40	1.6872	0.2198	1.6872	1.2989
No log	3.8182	42	1.5699	0.2075	1.5699	1.2529
No log	4.0	44	1.4360	0.2338	1.4360	1.1983
No log	4.1818	46	1.4985	0.1582	1.4985	1.2241
No log	4.3636	48	1.5642	0.0950	1.5642	1.2507
No log	4.5455	50	1.5495	0.0950	1.5495	1.2448
No log	4.7273	52	1.3760	0.1582	1.3760	1.1730
No log	4.9091	54	1.3113	0.2770	1.3113	1.1451
No log	5.0909	56	1.4035	0.2607	1.4035	1.1847
No log	5.2727	58	1.4266	0.2607	1.4266	1.1944
No log	5.4545	60	1.3690	0.3173	1.3690	1.1701
No log	5.6364	62	1.3720	0.3173	1.3720	1.1713
No log	5.8182	64	1.3692	0.3443	1.3692	1.1701
No log	6.0	66	1.4498	0.1876	1.4498	1.2041
No log	6.1818	68	1.4784	0.1876	1.4784	1.2159
No log	6.3636	70	1.4142	0.2006	1.4142	1.1892
No log	6.5455	72	1.3622	0.2597	1.3622	1.1671
No log	6.7273	74	1.3389	0.3443	1.3389	1.1571
No log	6.9091	76	1.3659	0.2380	1.3659	1.1687
No log	7.0909	78	1.4175	0.2380	1.4175	1.1906
No log	7.2727	80	1.4014	0.2380	1.4014	1.1838
No log	7.4545	82	1.3462	0.2380	1.3462	1.1603
No log	7.6364	84	1.2929	0.2770	1.2929	1.1371
No log	7.8182	86	1.2989	0.2597	1.2989	1.1397
No log	8.0	88	1.3861	0.2125	1.3861	1.1773
No log	8.1818	90	1.4672	0.2006	1.4672	1.2113
No log	8.3636	92	1.4616	0.2006	1.4616	1.2090
No log	8.5455	94	1.4006	0.2125	1.4006	1.1835
No log	8.7273	96	1.3339	0.2597	1.3339	1.1550
No log	8.9091	98	1.2928	0.2597	1.2928	1.1370
No log	9.0909	100	1.2647	0.2597	1.2647	1.1246
No log	9.2727	102	1.2438	0.2338	1.2438	1.1153
No log	9.4545	104	1.2326	0.2338	1.2326	1.1102
No log	9.6364	106	1.2267	0.2338	1.2267	1.1076
No log	9.8182	108	1.2221	0.2338	1.2221	1.1055
No log	10.0	110	1.2195	0.2338	1.2195	1.1043

Framework versions

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