arabert_baseline_vocabulary_task8_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: 0.2316
• Qwk: 0.8078
• Mse: 0.2316

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	1.2852	0.2500	1.2852
No log	1.0	4	0.9284	0.5172	0.9284
No log	1.5	6	0.5474	0.6196	0.5474
No log	2.0	8	0.4192	0.6172	0.4192
No log	2.5	10	0.3456	0.7627	0.3456
No log	3.0	12	0.3051	0.832	0.3051
No log	3.5	14	0.2935	0.7850	0.2935
No log	4.0	16	0.2662	0.8078	0.2662
No log	4.5	18	0.2641	0.832	0.2641
No log	5.0	20	0.2554	0.7956	0.2554
No log	5.5	22	0.2536	0.7956	0.2536
No log	6.0	24	0.2384	0.7956	0.2384
No log	6.5	26	0.2490	0.7956	0.2490
No log	7.0	28	0.2542	0.7956	0.2542
No log	7.5	30	0.2514	0.8269	0.2514
No log	8.0	32	0.2475	0.8409	0.2475
No log	8.5	34	0.2401	0.8078	0.2401
No log	9.0	36	0.2365	0.8078	0.2365
No log	9.5	38	0.2330	0.8078	0.2330
No log	10.0	40	0.2316	0.8078	0.2316

Framework versions

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