Cleverlytics/offres_classification_aubmindlab_bert-base-arabertv02_promo_classification_new_train_data_v1

offres_classification_UBC-NLP_MARBERT_promo_classification_new_train_data_v1

This model is a fine-tuned version of UBC-NLP/MARBERT on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0640

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-06
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	211	1.4751
No log	2.0	422	0.8215
1.4542	3.0	633	0.4444
1.4542	4.0	844	0.2632
0.4504	5.0	1055	0.1727
0.4504	6.0	1266	0.1351
0.4504	7.0	1477	0.0994
0.1381	8.0	1688	0.0911
0.1381	9.0	1899	0.0767
0.0581	10.0	2110	0.0790
0.0581	11.0	2321	0.0726
0.0383	12.0	2532	0.0691
0.0383	13.0	2743	0.0654
0.0383	14.0	2954	0.0669
0.0262	15.0	3165	0.0643
0.0262	16.0	3376	0.0653
0.0231	17.0	3587	0.0669
0.0231	18.0	3798	0.0647
0.0177	19.0	4009	0.0636
0.0177	20.0	4220	0.0640

Framework versions

• Transformers 4.50.3
• Pytorch 2.6.0+cu124
• Datasets 2.21.0
• Tokenizers 0.21.1