arabert_baseline_grammar_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: 0.2153
• Qwk: 0.2414
• Mse: 0.2131

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	2.7191	0.0489	2.7316
No log	1.3333	4	0.7628	0.0363	0.7728
No log	2.0	6	0.1911	0.0	0.1941
No log	2.6667	8	0.3562	0.4211	0.3479
No log	3.3333	10	0.3503	0.2326	0.3428
No log	4.0	12	0.2326	0.0	0.2296
No log	4.6667	14	0.2093	0.0	0.2075
No log	5.3333	16	0.2076	0.1538	0.2056
No log	6.0	18	0.2144	-0.0548	0.2124
No log	6.6667	20	0.2684	0.0833	0.2656
No log	7.3333	22	0.2806	0.3774	0.2776
No log	8.0	24	0.2555	0.3774	0.2530
No log	8.6667	26	0.2370	0.2414	0.2348
No log	9.3333	28	0.2195	0.2414	0.2174
No log	10.0	30	0.2153	0.2414	0.2131

Framework versions

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