BEREL_2.0-finetuned-samaritan_v2

This model is a fine-tuned version of dicta-il/BEREL_2.0 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 4.8497

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: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3.0
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
6.1303	1.0	97	5.2030
5.2194	2.0	194	4.9260
5.0335	3.0	291	4.8766

Framework versions

• Transformers 4.40.1
• Pytorch 2.3.0
• Datasets 2.19.0
• Tokenizers 0.19.1