offres_classification_bert_promo_classification_new_train_data_v2

This model is a fine-tuned version of SI2M-Lab/DarijaBERT on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0711

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: 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: 10

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	211	0.1140
No log	2.0	422	0.0729
0.292	3.0	633	0.0584
0.292	4.0	844	0.0479
0.0045	5.0	1055	0.0718
0.0045	6.0	1266	0.0703
0.0045	7.0	1477	0.0687
0.0016	8.0	1688	0.0678
0.0016	9.0	1899	0.0694
0.0016	10.0	2110	0.0711

Framework versions

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