arabert_no_augmentation_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: 0.8071
• Qwk: 0.7786
• Mse: 0.8071
• Rmse: 0.8984

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	4.6091	-0.0084	4.6091	2.1469
No log	0.3636	4	2.7511	0.0000	2.7511	1.6586
No log	0.5455	6	1.9010	-0.1625	1.9010	1.3788
No log	0.7273	8	1.2735	0.0930	1.2735	1.1285
No log	0.9091	10	1.3174	0.2584	1.3174	1.1478
No log	1.0909	12	1.2159	0.3084	1.2159	1.1027
No log	1.2727	14	1.1049	0.3923	1.1049	1.0511
No log	1.4545	16	0.9768	0.4541	0.9768	0.9883
No log	1.6364	18	1.2066	0.4134	1.2066	1.0985
No log	1.8182	20	1.4322	0.4085	1.4322	1.1967
No log	2.0	22	1.4533	0.3831	1.4533	1.2055
No log	2.1818	24	1.2317	0.5312	1.2317	1.1098
No log	2.3636	26	0.9282	0.4561	0.9282	0.9634
No log	2.5455	28	1.0926	0.5222	1.0926	1.0453
No log	2.7273	30	1.0693	0.5222	1.0693	1.0341
No log	2.9091	32	0.9590	0.5088	0.9590	0.9793
No log	3.0909	34	1.1455	0.5288	1.1455	1.0703
No log	3.2727	36	1.3818	0.5073	1.3818	1.1755
No log	3.4545	38	1.3091	0.5073	1.3091	1.1442
No log	3.6364	40	0.9953	0.5288	0.9953	0.9976
No log	3.8182	42	0.7863	0.4938	0.7863	0.8867
No log	4.0	44	0.8394	0.5254	0.8394	0.9162
No log	4.1818	46	0.7831	0.5399	0.7831	0.8849
No log	4.3636	48	0.7361	0.6087	0.7361	0.8580
No log	4.5455	50	1.0454	0.7268	1.0454	1.0224
No log	4.7273	52	1.2795	0.5743	1.2795	1.1312
No log	4.9091	54	1.2229	0.5896	1.2229	1.1058
No log	5.0909	56	1.0233	0.7526	1.0233	1.0116
No log	5.2727	58	0.8234	0.6087	0.8234	0.9074
No log	5.4545	60	0.7794	0.6087	0.7794	0.8828
No log	5.6364	62	0.8013	0.6087	0.8013	0.8952
No log	5.8182	64	0.8913	0.6182	0.8913	0.9441
No log	6.0	66	0.9996	0.6536	0.9996	0.9998
No log	6.1818	68	1.1340	0.6585	1.1340	1.0649
No log	6.3636	70	1.1480	0.6585	1.1480	1.0714
No log	6.5455	72	1.0158	0.7447	1.0158	1.0079
No log	6.7273	74	0.8611	0.6026	0.8611	0.9280
No log	6.9091	76	0.7947	0.6087	0.7947	0.8915
No log	7.0909	78	0.7768	0.6340	0.7768	0.8814
No log	7.2727	80	0.7826	0.5997	0.7826	0.8846
No log	7.4545	82	0.8277	0.7109	0.8277	0.9098
No log	7.6364	84	0.8633	0.7355	0.8633	0.9291
No log	7.8182	86	0.8868	0.7704	0.8868	0.9417
No log	8.0	88	0.9068	0.7704	0.9068	0.9523
No log	8.1818	90	0.9279	0.7704	0.9279	0.9633
No log	8.3636	92	0.8988	0.7955	0.8988	0.9481
No log	8.5455	94	0.8985	0.7955	0.8985	0.9479
No log	8.7273	96	0.8973	0.7955	0.8973	0.9473
No log	8.9091	98	0.8757	0.7955	0.8757	0.9358
No log	9.0909	100	0.8457	0.7955	0.8457	0.9196
No log	9.2727	102	0.8353	0.7786	0.8353	0.9140
No log	9.4545	104	0.8206	0.7786	0.8206	0.9059
No log	9.6364	106	0.8107	0.7786	0.8107	0.9004
No log	9.8182	108	0.8081	0.7786	0.8081	0.8990
No log	10.0	110	0.8071	0.7786	0.8071	0.8984

Framework versions

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