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_173154-sweep

Name: Bielik-1.5B-v3.0-Instruct-curriculum_1.5_finetuning-r-8-alpha-16-20250930_173154-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_173154-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: 975.9072

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: 0.07082326622170965
train_batch_size: 4
eval_batch_size: 4
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	0.0364	100	87880.9453
No log	0.0727	200	87920.1719
No log	0.1091	300	63176.0508
No log	0.1455	400	146250.8438
157531.248	0.1818	500	287449.3125
157531.248	0.2182	600	61463.3359
157531.248	0.2545	700	84303.9141
157531.248	0.2909	800	80890.2969
157531.248	0.3273	900	86683.2344
136843.568	0.3636	1000	57143.0977
136843.568	0.4	1100	149082.1719
136843.568	0.4364	1200	53047.9609
136843.568	0.4727	1300	92202.2578
136843.568	0.5091	1400	62214.7812
111345.288	0.5455	1500	87144.1094
111345.288	0.5818	1600	79826.2109
111345.288	0.6182	1700	150313.8906
111345.288	0.6545	1800	31356.2480
111345.288	0.6909	1900	27949.8008
70029.256	0.7273	2000	32975.9023
70029.256	0.7636	2100	20000.8223
70029.256	0.8	2200	49807.8516
70029.256	0.8364	2300	12118.4775
70029.256	0.8727	2400	92046.2188
24651.622	0.9091	2500	12648.8213
24651.622	0.9455	2600	7521.5352
24651.622	0.9818	2700	975.9072

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_173154-sweep

Bielik-1.5B-v3.0-Instruct-curriculum_1.5_finetuning-r-8-alpha-16-20250930_173154-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_173154-sweep