fine_tuned_student_kd_rag_freezing

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.6516

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
0.3876	1.0	5072	0.4729
0.3121	2.0	10144	0.5091
0.2943	3.0	15216	0.5276
0.25	4.0	20288	0.5393
0.2331	5.0	25360	0.5592
0.2208	6.0	30432	0.5678
0.1983	7.0	35504	0.5805
0.203	8.0	40576	0.5830
0.1809	9.0	45648	0.5971
0.1705	10.0	50720	0.6044
0.178	11.0	55792	0.6167
0.1653	12.0	60864	0.6202
0.1663	13.0	65936	0.6279
0.1582	14.0	71008	0.6311
0.1588	15.0	76080	0.6378
0.1551	16.0	81152	0.6415
0.1455	17.0	86224	0.6479
0.151	18.0	91296	0.6487
0.1522	19.0	96368	0.6509
0.1339	20.0	101440	0.6516

Framework versions

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