arabert_baseline_mechanics_task3_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: 0.5566
• Qwk: 0.0
• Mse: 0.5305

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	3.7370	0.0	3.7555
No log	1.3333	4	1.5390	-0.1333	1.5514
No log	2.0	6	0.7858	0.0	0.7770
No log	2.6667	8	0.5137	0.0	0.4817
No log	3.3333	10	0.4147	0.3333	0.3999
No log	4.0	12	0.4934	0.0	0.4740
No log	4.6667	14	0.9565	0.0	0.9273
No log	5.3333	16	0.5298	0.0	0.5083
No log	6.0	18	0.2987	0.4	0.2867
No log	6.6667	20	0.2974	0.4444	0.2843
No log	7.3333	22	0.3322	0.0	0.3152
No log	8.0	24	0.3977	0.0	0.3771
No log	8.6667	26	0.4974	0.0	0.4731
No log	9.3333	28	0.5573	0.0	0.5311
No log	10.0	30	0.5566	0.0	0.5305

Framework versions

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