Arabic_FineTuningAraBERT_noAug_task3_organization_fold1

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: 0.6174
• Qwk: 0.0120
• Mse: 0.6174
• Rmse: 0.7858

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	0.3333	2	4.3037	0.0153	4.3037	2.0745
No log	0.6667	4	2.2464	0.0	2.2464	1.4988
No log	1.0	6	1.0081	-0.0168	1.0081	1.0040
No log	1.3333	8	0.6535	0.0253	0.6535	0.8084
No log	1.6667	10	0.8673	0.0120	0.8673	0.9313
No log	2.0	12	0.7327	0.0120	0.7327	0.8560
No log	2.3333	14	0.7943	0.0120	0.7943	0.8912
No log	2.6667	16	0.8708	0.0	0.8708	0.9332
No log	3.0	18	0.7803	0.0	0.7803	0.8834
No log	3.3333	20	0.6282	0.0120	0.6282	0.7926
No log	3.6667	22	0.5509	0.2143	0.5509	0.7423
No log	4.0	24	0.5582	0.2443	0.5582	0.7471
No log	4.3333	26	0.5330	0.2143	0.5330	0.7301
No log	4.6667	28	0.5411	0.1646	0.5411	0.7356
No log	5.0	30	0.5874	0.0	0.5874	0.7664
No log	5.3333	32	0.6514	0.0	0.6514	0.8071
No log	5.6667	34	0.7315	0.0	0.7315	0.8553
No log	6.0	36	0.7363	0.0	0.7363	0.8581
No log	6.3333	38	0.6468	0.0120	0.6468	0.8042
No log	6.6667	40	0.5834	0.0120	0.5834	0.7638
No log	7.0	42	0.5718	0.0120	0.5718	0.7561
No log	7.3333	44	0.5732	0.0120	0.5732	0.7571
No log	7.6667	46	0.5866	0.0120	0.5866	0.7659
No log	8.0	48	0.5980	0.0120	0.5980	0.7733
No log	8.3333	50	0.6420	0.0120	0.6420	0.8012
No log	8.6667	52	0.6888	0.0120	0.6888	0.8299
No log	9.0	54	0.6809	0.0120	0.6809	0.8252
No log	9.3333	56	0.6553	0.0120	0.6553	0.8095
No log	9.6667	58	0.6276	0.0120	0.6276	0.7922
No log	10.0	60	0.6174	0.0120	0.6174	0.7858

Framework versions

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