lease_sk_ner_emph_all

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

• Loss: 0.0464

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	1358	0.0257
0.0462	2.0	2716	0.0230
0.0099	3.0	4074	0.0235
0.0099	4.0	5432	0.0280
0.0061	5.0	6790	0.0299
0.0045	6.0	8148	0.0286
0.0045	7.0	9506	0.0314
0.0033	8.0	10864	0.0356
0.0025	9.0	12222	0.0350
0.0025	10.0	13580	0.0358
0.0019	11.0	14938	0.0426
0.0015	12.0	16296	0.0412
0.0015	13.0	17654	0.0447
0.0012	14.0	19012	0.0457
0.0009	15.0	20370	0.0464

Framework versions

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