arabert_baseline_mechanics_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: 0.3250
• Qwk: 0.7258
• Mse: 0.3234

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	0.9603	0.2687	0.9651
No log	0.6667	4	0.6926	0.5364	0.7202
No log	1.0	6	0.7727	0.6067	0.8086
No log	1.3333	8	0.7221	0.3538	0.7310
No log	1.6667	10	0.6375	0.4368	0.6487
No log	2.0	12	0.5211	0.6263	0.5378
No log	2.3333	14	0.4993	0.5911	0.5125
No log	2.6667	16	0.5624	0.6433	0.5686
No log	3.0	18	0.5828	0.6023	0.5851
No log	3.3333	20	0.4962	0.6576	0.4985
No log	3.6667	22	0.4100	0.6702	0.4135
No log	4.0	24	0.4169	0.6702	0.4169
No log	4.3333	26	0.4947	0.6509	0.4883
No log	4.6667	28	0.6006	0.5556	0.5893
No log	5.0	30	0.5615	0.6121	0.5504
No log	5.3333	32	0.4063	0.6702	0.4018
No log	5.6667	34	0.3483	0.7083	0.3470
No log	6.0	36	0.3490	0.7258	0.3465
No log	6.3333	38	0.3721	0.7258	0.3681
No log	6.6667	40	0.3827	0.7337	0.3782
No log	7.0	42	0.4201	0.6757	0.4135
No log	7.3333	44	0.4186	0.6757	0.4120
No log	7.6667	46	0.3821	0.7337	0.3775
No log	8.0	48	0.3398	0.7258	0.3377
No log	8.3333	50	0.3148	0.7258	0.3139
No log	8.6667	52	0.3098	0.7258	0.3091
No log	9.0	54	0.3110	0.7258	0.3101
No log	9.3333	56	0.3160	0.7258	0.3149
No log	9.6667	58	0.3224	0.7258	0.3209
No log	10.0	60	0.3250	0.7258	0.3234

Framework versions

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