You can deploy this model and start earning money today!

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

Name: Bielik-1.5B-v3.0-Instruct-curriculum_1.5_finetuning-r-8-alpha-16-20250930_230046-sweep
Availability: InStock

speakleash/Bielik-1.5B-v3.0-Instruct

apache-2.0

Views

No views yet

Bielik-1.5B-v3.0-Instruct-curriculum_1.5_finetuning-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
train_batch_size: 2
eval_batch_size: 2
seed: 42
optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 2
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0182	100	21091.7129
No log	0.0364	200	64379.8477
No log	0.0545	300	24325.0938
No log	0.0727	400	30580.1875
41463.768	0.0909	500	30718.2109
41463.768	0.1091	600	15634.6904
41463.768	0.1273	700	18437.6074
41463.768	0.1455	800	10014.7520
41463.768	0.1636	900	20060.0527
29813.578	0.1818	1000	18996.8535
29813.578	0.2	1100	28221.0957
29813.578	0.2182	1200	17184.1738
29813.578	0.2364	1300	18951.4199
29813.578	0.2545	1400	11519.8779
29219.446	0.2727	1500	18188.3672
29219.446	0.2909	1600	14285.6504
29219.446	0.3091	1700	8706.9717
29219.446	0.3273	1800	11534.7891
29219.446	0.3455	1900	20361.1973
23970.574	0.3636	2000	106175.7891
23970.574	0.3818	2100	6441.2109
23970.574	0.4	2200	11462.6143
23970.574	0.4182	2300	31587.9512
23970.574	0.4364	2400	5629.7324
23019.792	0.4545	2500	4941.4678
23019.792	0.4727	2600	4098.4663
23019.792	0.4909	2700	7639.1709
23019.792	0.5091	2800	35811.5742
23019.792	0.5273	2900	5676.0801
14440.096	0.5455	3000	6614.5557
14440.096	0.5636	3100	7977.9976
14440.096	0.5818	3200	4736.875
14440.096	0.6	3300	4246.8560
14440.096	0.6182	3400	2505.9480
13270.072	0.6364	3500	2310.5029
13270.072	0.6545	3600	30242.9062
13270.072	0.6727	3700	2248.9097
13270.072	0.6909	3800	3853.1531
13270.072	0.7091	3900	2261.4314
10049.75	0.7273	4000	1482.7972
10049.75	0.7455	4100	4152.8813
10049.75	0.7636	4200	2169.4885
10049.75	0.7818	4300	2349.9934
10049.75	0.8	4400	2255.7346
4162.3525	0.8182	4500	1826.6123
4162.3525	0.8364	4600	626.4967
4162.3525	0.8545	4700	1378.9613
4162.3525	0.8727	4800	652.9688
4162.3525	0.8909	4900	513.0810
2672.0682	0.9091	5000	3989.2314
2672.0682	0.9273	5100	293.7177
2672.0682	0.9455	5200	323.8909
2672.0682	0.9636	5300	252.1712
2672.0682	0.9818	5400	157.5715
790.5566	1.0	5500	143.7209

Framework versions

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

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

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

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

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