BEREL-finetuned-DSS-composition-classification

This model is a fine-tuned version of dicta-il/BEREL on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.5561

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: 7

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	37	2.5131
No log	2.0	74	2.1557
No log	3.0	111	1.9236
No log	4.0	148	1.7455
No log	5.0	185	1.6608
No log	6.0	222	1.5844
No log	7.0	259	1.5561

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1