arabert_baseline_vocabulary_task3_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: 0.2325
• Qwk: 0.2857
• Mse: 0.2437

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	0.6667	2	3.6484	0.0328	3.6411
No log	1.3333	4	1.3150	0.0541	1.3226
No log	2.0	6	0.2810	0.0	0.2941
No log	2.6667	8	0.2059	0.0	0.2199
No log	3.3333	10	0.2435	0.0	0.2582
No log	4.0	12	0.2557	0.0	0.2715
No log	4.6667	14	0.2138	0.0	0.2290
No log	5.3333	16	0.2031	0.0	0.2168
No log	6.0	18	0.2284	0.0	0.2412
No log	6.6667	20	0.2060	0.2857	0.2178
No log	7.3333	22	0.2168	0.2857	0.2280
No log	8.0	24	0.2244	0.2857	0.2354
No log	8.6667	26	0.2313	0.2857	0.2422
No log	9.3333	28	0.2311	0.2857	0.2422
No log	10.0	30	0.2325	0.2857	0.2437

Framework versions

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