arabert_baseline_style_task1_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: 0.4983
• Qwk: 0.5052
• Mse: 0.4984

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	5.8113	-0.0102	5.7669
No log	0.6667	4	2.3576	0.0342	2.3554
No log	1.0	6	1.4911	0.0652	1.4969
No log	1.3333	8	0.7580	0.1021	0.7628
No log	1.6667	10	0.5619	0.2851	0.5662
No log	2.0	12	0.6485	0.0870	0.6536
No log	2.3333	14	1.0404	0.1138	1.0530
No log	2.6667	16	0.6654	0.2646	0.6722
No log	3.0	18	0.4343	0.3425	0.4348
No log	3.3333	20	0.4318	0.4057	0.4340
No log	3.6667	22	0.4542	0.4057	0.4579
No log	4.0	24	0.5421	0.3191	0.5486
No log	4.3333	26	0.4470	0.3780	0.4507
No log	4.6667	28	0.4369	0.5130	0.4397
No log	5.0	30	0.4435	0.5130	0.4458
No log	5.3333	32	0.4758	0.6488	0.4772
No log	5.6667	34	0.5072	0.5130	0.5092
No log	6.0	36	0.5982	0.4160	0.6024
No log	6.3333	38	0.6201	0.3368	0.6243
No log	6.6667	40	0.5336	0.4731	0.5349
No log	7.0	42	0.5080	0.6613	0.5072
No log	7.3333	44	0.4953	0.6613	0.4944
No log	7.6667	46	0.4884	0.5689	0.4879
No log	8.0	48	0.4997	0.5052	0.4999
No log	8.3333	50	0.5187	0.4731	0.5194
No log	8.6667	52	0.5092	0.4731	0.5095
No log	9.0	54	0.4978	0.5052	0.4977
No log	9.3333	56	0.4999	0.5052	0.5000
No log	9.6667	58	0.5004	0.5052	0.5006
No log	10.0	60	0.4983	0.5052	0.4984

Framework versions

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