arabert_baseline_grammar_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: 0.6034
• Qwk: 0.0
• Mse: 0.6123

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	3.3662	-0.0117	3.3080
No log	1.3333	4	1.1203	-0.1172	1.0755
No log	2.0	6	0.8683	-0.1134	0.8544
No log	2.6667	8	0.6489	-0.0476	0.6406
No log	3.3333	10	0.4735	-0.0476	0.4763
No log	4.0	12	0.3822	-0.0476	0.3821
No log	4.6667	14	0.5267	-0.0476	0.5316
No log	5.3333	16	0.4612	-0.0476	0.4639
No log	6.0	18	0.3363	0.3529	0.3349
No log	6.6667	20	0.3888	-0.0476	0.3896
No log	7.3333	22	0.4637	-0.0476	0.4673
No log	8.0	24	0.5117	0.0	0.5172
No log	8.6667	26	0.5877	0.0	0.5954
No log	9.3333	28	0.6138	0.0	0.6226
No log	10.0	30	0.6034	0.0	0.6123

Framework versions

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