CoolFace
Modelpublic

zhendrysiak/Bielik-1.5B-v3.0-Instruct-curriculum_1.5_finetuning-r-8-alpha-16-02022025_hq

sourceHugging Faceapache-2.0updated 1y agoView on Hugging Face
0likes18downloads
Model Card

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

Bielik-1.5B-v3.0-Instruct-curriculum1.5finetuning-r-8-alpha-16-02022025_hq

This model is a fine-tuned version of speakleash/Bielik-1.5B-v3.0-Instruct on the None dataset. It achieves the following results on the evaluation set:

  • —Loss: 5.7614

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: 2.5e-05
  • —trainbatchsize: 2
  • —evalbatchsize: 2
  • —seed: 42
  • —optimizer: Use OptimizerNames.PAGEDADAMW8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • —lrschedulertype: linear
  • —lrschedulerwarmup_steps: 2
  • —num_epochs: 1

Training results

Training LossEpochStepValidation Loss
No log0.018210012.5293
No log0.036420010.1298
No log0.05453007.0587
No log0.07274005.9852
8.98350.09095005.9037
8.98350.10916005.8939
8.98350.12737005.8913
8.98350.14558005.8954
8.98350.16369005.8910
5.59760.181810005.8805
5.59760.211005.8667
5.59760.218212005.8581
5.59760.236413005.8505
5.59760.254514005.8495
5.80280.272715005.8447
5.80280.290916005.8405
5.80280.309117005.8359
5.80280.327318005.8341
5.80280.345519005.8268
5.5840.363620005.8236
5.5840.381821005.8195
5.5840.422005.8164
5.5840.418223005.8129
5.5840.436424005.8103
5.67330.454525005.8065
5.67330.472726005.8021
5.67330.490927005.8020
5.67330.509128005.7963
5.67330.527329005.7898
5.770.545530005.7866
5.770.563631005.7864
5.770.581832005.7858
5.770.633005.7857
5.770.618234005.7815
5.55040.636435005.7805
5.55040.654536005.7782
5.55040.672737005.7793
5.55040.690938005.7765
5.55040.709139005.7725
5.78350.727340005.7691
5.78350.745541005.7673
5.78350.763642005.7673
5.78350.781843005.7663
5.78350.844005.7665
5.69450.818245005.7662
5.69450.836446005.7655
5.69450.854547005.7654
5.69450.872748005.7650
5.69450.890949005.7647
5.52030.909150005.7636
5.52030.927351005.7630
5.52030.945552005.7628
5.52030.963653005.7615
5.52030.981854005.7614
5.59781.055005.7614

Framework versions

  • —PEFT 0.17.1
  • —Transformers 4.56.2
  • —Pytorch 2.8.0+cu126
  • —Datasets 4.0.0
  • —Tokenizers 0.22.1