CoolFace
Modelpublic

zhendrysiak/Bielik-1.5B-v3.0-Instruct-curriculum_1.5_finetuning-r-8-alpha-16-20250930_192823-sweep

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-16-20250930_192823-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: 200.7851

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: 0.027164780344994467
  • —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 log0.018210037601.8477
No log0.036420027159.8691
No log0.0545300133996.7188
No log0.072740059184.4883
75669.9920.090950056441.4570
75669.9920.109160037787.9336
75669.9920.127370051527.1797
75669.9920.145580086344.625
75669.9920.163690024727.9434
47590.3320.1818100053946.2891
47590.3320.2110033183.1367
47590.3320.2182120023832.4023
47590.3320.2364130035160.3359
47590.3320.2545140014669.3740
42691.9280.2727150022424.9102
42691.9280.2909160019346.4395
42691.9280.3091170019345.1289
42691.9280.3273180022866.7891
42691.9280.3455190020333.1191
32700.4360.3636200016086.3047
32700.4360.3818210021233.0801
32700.4360.4220012537.8457
32700.4360.4182230021467.9805
32700.4360.4364240012332.1611
18403.6880.454525007200.1206
18403.6880.4727260012898.6523
18403.6880.4909270012314.9971
18403.6880.509128006598.1533
18403.6880.5273290011986.6270
15734.3870.545530009139.9766
15734.3870.5636310019325.8555
15734.3870.5818320018628.2422
15734.3870.6330011303.5439
15734.3870.618234007348.3506
11461.8650.636435005723.6108
11461.8650.654536009962.7549
11461.8650.672737004647.6816
11461.8650.690938004203.7935
11461.8650.709139004643.5073
8142.1370.727340003357.4270
8142.1370.7455410021111.4805
8142.1370.763642005119.8340
8142.1370.781843004294.9761
8142.1370.844003878.6060
5066.28950.818245002551.5288
5066.28950.836446002393.6023
5066.28950.854547002328.6333
5066.28950.872748001141.1940
5066.28950.890949004037.4465
3104.24920.90915000513.4738
3104.24920.92735100896.4385
3104.24920.94555200321.9753
3104.24920.96365300287.7932
3104.24920.98185400173.4742
662.47391.05500200.7851

Framework versions

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