arabert_baseline_mechanics_task2_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: 0.9842
• Qwk: 0.1750
• Mse: 0.9841

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	0.3333	2	4.1574	0.0205	4.1715
No log	0.6667	4	2.0929	0.0123	2.1054
No log	1.0	6	1.3194	-0.1337	1.3202
No log	1.3333	8	0.9360	0.2588	0.9322
No log	1.6667	10	0.9386	0.0907	0.9344
No log	2.0	12	1.1338	-0.0221	1.1277
No log	2.3333	14	1.0683	0.0907	1.0627
No log	2.6667	16	0.8193	0.2808	0.8154
No log	3.0	18	0.7951	0.2441	0.7912
No log	3.3333	20	0.8524	0.2853	0.8486
No log	3.6667	22	1.0382	-0.1210	1.0361
No log	4.0	24	1.2097	-0.1351	1.2090
No log	4.3333	26	1.3025	-0.0355	1.3038
No log	4.6667	28	1.1375	0.2732	1.1373
No log	5.0	30	0.8628	0.2455	0.8539
No log	5.3333	32	0.8145	0.1649	0.8046
No log	5.6667	34	0.8765	0.2222	0.8718
No log	6.0	36	0.9949	0.1892	0.9951
No log	6.3333	38	1.0164	0.1892	1.0171
No log	6.6667	40	0.9913	0.1892	0.9919
No log	7.0	42	0.9485	0.1892	0.9484
No log	7.3333	44	0.9129	0.0667	0.9120
No log	7.6667	46	0.8943	0.0667	0.8925
No log	8.0	48	0.9394	0.0667	0.9387
No log	8.3333	50	0.9883	0.1892	0.9886
No log	8.6667	52	0.9904	0.1892	0.9907
No log	9.0	54	0.9905	0.1892	0.9908
No log	9.3333	56	0.9842	0.1892	0.9843
No log	9.6667	58	0.9876	0.1664	0.9876
No log	10.0	60	0.9842	0.1750	0.9841

Framework versions

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