arabert_baseline_mechanics_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: 0.2956
• Qwk: -0.1647
• Mse: 0.2733

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	2.9227	0.0560	2.9630
No log	1.3333	4	0.8415	0.0733	0.8632
No log	2.0	6	0.1950	0.0	0.1826
No log	2.6667	8	0.3611	-0.3200	0.3329
No log	3.3333	10	0.4100	-0.1818	0.3921
No log	4.0	12	0.4163	-0.0312	0.4025
No log	4.6667	14	0.2671	-0.1647	0.2475
No log	5.3333	16	0.2529	-0.2222	0.2308
No log	6.0	18	0.2479	-0.2791	0.2261
No log	6.6667	20	0.2690	0.1200	0.2457
No log	7.3333	22	0.2675	-0.1647	0.2467
No log	8.0	24	0.3012	-0.1647	0.2826
No log	8.6667	26	0.3080	-0.1647	0.2883
No log	9.3333	28	0.2986	-0.1647	0.2773
No log	10.0	30	0.2956	-0.1647	0.2733

Framework versions

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