arabert_baseline_style_task8_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: 0.3136
• Qwk: 0.7317
• Mse: 0.3136

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: 16
• eval_batch_size: 16
• 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
No log	0.5	2	1.6518	0.0571	1.6518
No log	1.0	4	1.0371	0.4444	1.0371
No log	1.5	6	0.7388	0.5366	0.7388
No log	2.0	8	1.1938	0.36	1.1938
No log	2.5	10	0.4631	0.6667	0.4631
No log	3.0	12	0.2492	0.7179	0.2492
No log	3.5	14	0.2694	0.7179	0.2694
No log	4.0	16	0.4368	0.6341	0.4368
No log	4.5	18	0.7618	0.5909	0.7618
No log	5.0	20	0.6253	0.5909	0.6253
No log	5.5	22	0.3729	0.7	0.3729
No log	6.0	24	0.2843	0.75	0.2843
No log	6.5	26	0.3066	0.75	0.3066
No log	7.0	28	0.3650	0.7317	0.3650
No log	7.5	30	0.4196	0.6341	0.4196
No log	8.0	32	0.3773	0.6667	0.3773
No log	8.5	34	0.3197	0.7317	0.3197
No log	9.0	36	0.3106	0.7317	0.3106
No log	9.5	38	0.3073	0.7317	0.3073
No log	10.0	40	0.3136	0.7317	0.3136

Framework versions

• Transformers 4.44.0
• Pytorch 2.4.0
• Datasets 2.21.0
• Tokenizers 0.19.1