CoolFace
Modelpublic

zhendrysiak/Bielik-1.5B-v3.0-Instruct-curriculum_1.5_finetuning-r-8-alpha-16-20250930_230046-sweep

sourceHugging Faceapache-2.0updated 1y agoView on Hugging Face
0likes19downloads
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-16-20250930_230046-sweep

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: 143.7209

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: 0.03509572046095939
  • —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 log0.018210021091.7129
No log0.036420064379.8477
No log0.054530024325.0938
No log0.072740030580.1875
41463.7680.090950030718.2109
41463.7680.109160015634.6904
41463.7680.127370018437.6074
41463.7680.145580010014.7520
41463.7680.163690020060.0527
29813.5780.1818100018996.8535
29813.5780.2110028221.0957
29813.5780.2182120017184.1738
29813.5780.2364130018951.4199
29813.5780.2545140011519.8779
29219.4460.2727150018188.3672
29219.4460.2909160014285.6504
29219.4460.309117008706.9717
29219.4460.3273180011534.7891
29219.4460.3455190020361.1973
23970.5740.36362000106175.7891
23970.5740.381821006441.2109
23970.5740.4220011462.6143
23970.5740.4182230031587.9512
23970.5740.436424005629.7324
23019.7920.454525004941.4678
23019.7920.472726004098.4663
23019.7920.490927007639.1709
23019.7920.5091280035811.5742
23019.7920.527329005676.0801
14440.0960.545530006614.5557
14440.0960.563631007977.9976
14440.0960.581832004736.875
14440.0960.633004246.8560
14440.0960.618234002505.9480
13270.0720.636435002310.5029
13270.0720.6545360030242.9062
13270.0720.672737002248.9097
13270.0720.690938003853.1531
13270.0720.709139002261.4314
10049.750.727340001482.7972
10049.750.745541004152.8813
10049.750.763642002169.4885
10049.750.781843002349.9934
10049.750.844002255.7346
4162.35250.818245001826.6123
4162.35250.83644600626.4967
4162.35250.854547001378.9613
4162.35250.87274800652.9688
4162.35250.89094900513.0810
2672.06820.909150003989.2314
2672.06820.92735100293.7177
2672.06820.94555200323.8909
2672.06820.96365300252.1712
2672.06820.98185400157.5715
790.55661.05500143.7209

Framework versions

  • —PEFT 0.17.1
  • —Transformers 4.56.1
  • —Pytorch 2.8.0+cu126
  • —Datasets 4.0.0
  • —Tokenizers 0.22.0