arabert_baseline_relevance_task6_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: 0.2487
• Qwk: 0.4545
• Mse: 0.2487

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	0.5	2	0.2676	0.2727	0.2676
No log	1.0	4	0.3056	0.2727	0.3056
No log	1.5	6	0.2873	0.3636	0.2873
No log	2.0	8	0.3326	0.3636	0.3326
No log	2.5	10	0.2924	0.3636	0.2924
No log	3.0	12	0.2560	0.3636	0.2560
No log	3.5	14	0.2341	0.3636	0.2341
No log	4.0	16	0.2402	0.4545	0.2402
No log	4.5	18	0.2513	0.4545	0.2513
No log	5.0	20	0.2596	0.4545	0.2596
No log	5.5	22	0.2641	0.4545	0.2641
No log	6.0	24	0.2500	0.4545	0.2500
No log	6.5	26	0.2509	0.4545	0.2509
No log	7.0	28	0.2495	0.4545	0.2495
No log	7.5	30	0.2478	0.4545	0.2478
No log	8.0	32	0.2467	0.4545	0.2467
No log	8.5	34	0.2479	0.4545	0.2479
No log	9.0	36	0.2484	0.4545	0.2484
No log	9.5	38	0.2486	0.4545	0.2486
No log	10.0	40	0.2487	0.4545	0.2487

Framework versions

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