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_192823-sweep

Name: Bielik-1.5B-v3.0-Instruct-curriculum_1.5_finetuning-r-8-alpha-16-20250930_192823-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_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
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	37601.8477
No log	0.0364	200	27159.8691
No log	0.0545	300	133996.7188
No log	0.0727	400	59184.4883
75669.992	0.0909	500	56441.4570
75669.992	0.1091	600	37787.9336
75669.992	0.1273	700	51527.1797
75669.992	0.1455	800	86344.625
75669.992	0.1636	900	24727.9434
47590.332	0.1818	1000	53946.2891
47590.332	0.2	1100	33183.1367
47590.332	0.2182	1200	23832.4023
47590.332	0.2364	1300	35160.3359
47590.332	0.2545	1400	14669.3740
42691.928	0.2727	1500	22424.9102
42691.928	0.2909	1600	19346.4395
42691.928	0.3091	1700	19345.1289
42691.928	0.3273	1800	22866.7891
42691.928	0.3455	1900	20333.1191
32700.436	0.3636	2000	16086.3047
32700.436	0.3818	2100	21233.0801
32700.436	0.4	2200	12537.8457
32700.436	0.4182	2300	21467.9805
32700.436	0.4364	2400	12332.1611
18403.688	0.4545	2500	7200.1206
18403.688	0.4727	2600	12898.6523
18403.688	0.4909	2700	12314.9971
18403.688	0.5091	2800	6598.1533
18403.688	0.5273	2900	11986.6270
15734.387	0.5455	3000	9139.9766
15734.387	0.5636	3100	19325.8555
15734.387	0.5818	3200	18628.2422
15734.387	0.6	3300	11303.5439
15734.387	0.6182	3400	7348.3506
11461.865	0.6364	3500	5723.6108
11461.865	0.6545	3600	9962.7549
11461.865	0.6727	3700	4647.6816
11461.865	0.6909	3800	4203.7935
11461.865	0.7091	3900	4643.5073
8142.137	0.7273	4000	3357.4270
8142.137	0.7455	4100	21111.4805
8142.137	0.7636	4200	5119.8340
8142.137	0.7818	4300	4294.9761
8142.137	0.8	4400	3878.6060
5066.2895	0.8182	4500	2551.5288
5066.2895	0.8364	4600	2393.6023
5066.2895	0.8545	4700	2328.6333
5066.2895	0.8727	4800	1141.1940
5066.2895	0.8909	4900	4037.4465
3104.2492	0.9091	5000	513.4738
3104.2492	0.9273	5100	896.4385
3104.2492	0.9455	5200	321.9753
3104.2492	0.9636	5300	287.7932
3104.2492	0.9818	5400	173.4742
662.4739	1.0	5500	200.7851

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_192823-sweep

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