ArabicNewSplits6_FineTuningAraBERT_run3_AugV5_k1_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: 0.7989
• Qwk: 0.4281
• Mse: 0.7989
• Rmse: 0.8938

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	0.2857	2	3.9869	-0.0048	3.9869	1.9967
No log	0.5714	4	1.9168	0.0480	1.9168	1.3845
No log	0.8571	6	1.0607	0.0569	1.0607	1.0299
No log	1.1429	8	0.7994	0.0531	0.7994	0.8941
No log	1.4286	10	0.7178	0.2111	0.7178	0.8473
No log	1.7143	12	0.7635	0.1187	0.7635	0.8738
No log	2.0	14	0.8129	0.0863	0.8129	0.9016
No log	2.2857	16	0.7605	0.1372	0.7605	0.8721
No log	2.5714	18	0.7705	0.1886	0.7705	0.8778
No log	2.8571	20	0.8571	0.2867	0.8571	0.9258
No log	3.1429	22	0.8777	0.2906	0.8777	0.9369
No log	3.4286	24	0.7496	0.2772	0.7496	0.8658
No log	3.7143	26	0.6798	0.3594	0.6798	0.8245
No log	4.0	28	0.9203	0.2216	0.9203	0.9593
No log	4.2857	30	1.0449	0.1946	1.0449	1.0222
No log	4.5714	32	0.9119	0.2755	0.9119	0.9549
No log	4.8571	34	0.6827	0.3717	0.6827	0.8263
No log	5.1429	36	0.6388	0.3622	0.6388	0.7992
No log	5.4286	38	0.6561	0.3611	0.6561	0.8100
No log	5.7143	40	0.6766	0.3879	0.6766	0.8225
No log	6.0	42	0.7158	0.3906	0.7158	0.8461
No log	6.2857	44	0.8083	0.3253	0.8083	0.8991
No log	6.5714	46	0.8923	0.2988	0.8923	0.9446
No log	6.8571	48	0.8738	0.3163	0.8738	0.9348
No log	7.1429	50	0.8260	0.3257	0.8260	0.9089
No log	7.4286	52	0.8205	0.3257	0.8205	0.9058
No log	7.7143	54	0.7930	0.3861	0.7930	0.8905
No log	8.0	56	0.7757	0.4225	0.7757	0.8807
No log	8.2857	58	0.7818	0.4487	0.7818	0.8842
No log	8.5714	60	0.7893	0.4324	0.7893	0.8884
No log	8.8571	62	0.7966	0.4222	0.7966	0.8925
No log	9.1429	64	0.7980	0.4143	0.7980	0.8933
No log	9.4286	66	0.7997	0.4181	0.7997	0.8942
No log	9.7143	68	0.7993	0.4181	0.7993	0.8940
No log	10.0	70	0.7989	0.4281	0.7989	0.8938

Framework versions

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