lease_sk_ner_non_emph

This model is a fine-tuned version of gerulata/slovakbert on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0422

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: 2e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	1172	0.0260
0.0461	2.0	2344	0.0216
0.0461	3.0	3516	0.0228
0.0101	4.0	4688	0.0260
0.0101	5.0	5860	0.0281
0.0063	6.0	7032	0.0284
0.0044	7.0	8204	0.0328
0.0044	8.0	9376	0.0321
0.0032	9.0	10548	0.0361
0.0032	10.0	11720	0.0359
0.0024	11.0	12892	0.0378
0.0018	12.0	14064	0.0391
0.0018	13.0	15236	0.0397
0.0014	14.0	16408	0.0407
0.0014	15.0	17580	0.0422

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.0.1
• Tokenizers 0.19.1