fine_tuned_student_kd_rag_3

This model is a fine-tuned version of MarZaf/fine_tuned_student_kd_transformer-augmented4.1 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0936

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use paged_adamw_32bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 20
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.1775	1.0	5072	0.0731
0.1368	2.0	10144	0.0794
0.116	3.0	15216	0.0831
0.0951	4.0	20288	0.0866
0.0859	5.0	25360	0.0902
0.0735	6.0	30432	0.0936

Framework versions

• Transformers 4.51.3
• Pytorch 2.7.0+cu126
• Datasets 3.6.0
• Tokenizers 0.21.2