arabert_baseline_mechanics_task4_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: 0.6930
• Qwk: 0.0
• Mse: 0.6930

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	1.0	2	2.5168	-0.0385	2.5168
No log	2.0	4	0.7942	0.0625	0.7942
No log	3.0	6	0.4547	0.125	0.4547
No log	4.0	8	0.6479	0.3333	0.6479
No log	5.0	10	0.6637	0.5	0.6637
No log	6.0	12	0.7552	0.0	0.7552
No log	7.0	14	0.7813	0.1667	0.7813
No log	8.0	16	0.7229	0.0	0.7229
No log	9.0	18	0.6995	0.0	0.6995
No log	10.0	20	0.6930	0.0	0.6930

Framework versions

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