arabert_baseline_organization_task7_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: 0.6217
• Qwk: 0.4969
• Mse: 0.6213

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	1.0245	0.3758	1.0297
No log	0.6667	4	0.7919	0.5312	0.8059
No log	1.0	6	0.8469	0.6400	0.8626
No log	1.3333	8	0.7621	0.3793	0.7785
No log	1.6667	10	0.8831	0.2326	0.8970
No log	2.0	12	0.7493	0.4	0.7628
No log	2.3333	14	0.4924	0.6165	0.5052
No log	2.6667	16	0.4499	0.6571	0.4612
No log	3.0	18	0.4936	0.6203	0.5029
No log	3.3333	20	0.7252	0.4224	0.7311
No log	3.6667	22	0.9227	0.3657	0.9263
No log	4.0	24	0.8957	0.3657	0.8980
No log	4.3333	26	0.7242	0.4211	0.7260
No log	4.6667	28	0.5595	0.6203	0.5620
No log	5.0	30	0.4521	0.6024	0.4559
No log	5.3333	32	0.4402	0.6786	0.4437
No log	5.6667	34	0.4703	0.6909	0.4728
No log	6.0	36	0.6144	0.5	0.6153
No log	6.3333	38	0.7150	0.4969	0.7150
No log	6.6667	40	0.7022	0.4969	0.7024
No log	7.0	42	0.6409	0.5	0.6418
No log	7.3333	44	0.5912	0.5	0.5923
No log	7.6667	46	0.5457	0.6341	0.5469
No log	8.0	48	0.5073	0.6909	0.5089
No log	8.3333	50	0.5143	0.6909	0.5157
No log	8.6667	52	0.5540	0.6341	0.5549
No log	9.0	54	0.5883	0.6272	0.5886
No log	9.3333	56	0.6103	0.4969	0.6102
No log	9.6667	58	0.6204	0.4969	0.6200
No log	10.0	60	0.6217	0.4969	0.6213

Framework versions

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