ArabicNewSplits6_WithDuplicationsForScore5_FineTuningAraBERT_run3_AugV5_k2_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: 1.1626
• Qwk: 0.6083
• Mse: 1.1626
• Rmse: 1.0782

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	2.3491	-0.0013	2.3491	1.5327
No log	0.3636	4	1.4925	0.2017	1.4925	1.2217
No log	0.5455	6	1.3164	0.1307	1.3164	1.1474
No log	0.7273	8	1.3824	0.1903	1.3824	1.1757
No log	0.9091	10	1.6964	0.3128	1.6964	1.3024
No log	1.0909	12	1.8682	0.3116	1.8682	1.3668
No log	1.2727	14	1.8846	0.3128	1.8846	1.3728
No log	1.4545	16	1.7012	0.3448	1.7012	1.3043
No log	1.6364	18	1.4895	0.3223	1.4895	1.2204
No log	1.8182	20	1.3364	0.2865	1.3364	1.1560
No log	2.0	22	1.2644	0.1628	1.2644	1.1245
No log	2.1818	24	1.2313	0.1903	1.2313	1.1096
No log	2.3636	26	1.1790	0.1628	1.1790	1.0858
No log	2.5455	28	1.1314	0.2202	1.1314	1.0637
No log	2.7273	30	1.1207	0.3277	1.1207	1.0586
No log	2.9091	32	1.1514	0.3766	1.1514	1.0730
No log	3.0909	34	1.2195	0.3711	1.2195	1.1043
No log	3.2727	36	1.3770	0.4037	1.3770	1.1735
No log	3.4545	38	1.4887	0.3906	1.4887	1.2201
No log	3.6364	40	1.4150	0.3902	1.4150	1.1895
No log	3.8182	42	1.2434	0.4161	1.2434	1.1151
No log	4.0	44	1.0707	0.4686	1.0707	1.0347
No log	4.1818	46	0.9741	0.5035	0.9741	0.9869
No log	4.3636	48	0.9428	0.5262	0.9428	0.9710
No log	4.5455	50	0.9151	0.5649	0.9151	0.9566
No log	4.7273	52	0.9797	0.5462	0.9797	0.9898
No log	4.9091	54	1.1162	0.5336	1.1162	1.0565
No log	5.0909	56	1.2237	0.4909	1.2237	1.1062
No log	5.2727	58	1.2223	0.5082	1.2223	1.1056
No log	5.4545	60	1.2128	0.5309	1.2128	1.1013
No log	5.6364	62	1.1364	0.4918	1.1364	1.0660
No log	5.8182	64	1.0813	0.4683	1.0813	1.0399
No log	6.0	66	1.0827	0.5036	1.0827	1.0405
No log	6.1818	68	1.0956	0.5647	1.0956	1.0467
No log	6.3636	70	1.0943	0.5571	1.0943	1.0461
No log	6.5455	72	1.0891	0.5477	1.0891	1.0436
No log	6.7273	74	1.0977	0.5642	1.0977	1.0477
No log	6.9091	76	1.0979	0.5645	1.0979	1.0478
No log	7.0909	78	1.1484	0.5521	1.1484	1.0716
No log	7.2727	80	1.1266	0.5567	1.1266	1.0614
No log	7.4545	82	1.1001	0.5791	1.1001	1.0488
No log	7.6364	84	1.0252	0.5918	1.0252	1.0125
No log	7.8182	86	0.9597	0.5946	0.9597	0.9797
No log	8.0	88	0.9549	0.6095	0.9549	0.9772
No log	8.1818	90	0.9901	0.6134	0.9901	0.9950
No log	8.3636	92	1.0505	0.6174	1.0505	1.0249
No log	8.5455	94	1.1476	0.6083	1.1476	1.0713
No log	8.7273	96	1.2085	0.5830	1.2085	1.0993
No log	8.9091	98	1.2312	0.5551	1.2312	1.1096
No log	9.0909	100	1.2390	0.5551	1.2390	1.1131
No log	9.2727	102	1.2360	0.5551	1.2360	1.1117
No log	9.4545	104	1.2087	0.5871	1.2087	1.0994
No log	9.6364	106	1.1831	0.5956	1.1831	1.0877
No log	9.8182	108	1.1679	0.6083	1.1679	1.0807
No log	10.0	110	1.1626	0.6083	1.1626	1.0782

Framework versions

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