README.md

metadata

library_name: transformers
base_model: skt/kobert-base-v1
tags:
  - generated_from_trainer
metrics:
  - f1
  - precision
  - recall
model-index:
  - name: GS_bert
    results: []

GS_bert

This model is a fine-tuned version of skt/kobert-base-v1 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.1479
• F1: 0.2907
• Precision: 0.3056
• Recall: 0.2796

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: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	F1	Precision	Recall
0.1873	1.0	90	0.1755	0.0291	0.0315	0.0273
0.1681	2.0	180	0.1618	0.0381	0.0407	0.0361
0.1692	3.0	270	0.1617	0.0421	0.0444	0.0403
0.1715	4.0	360	0.1616	0.0397	0.0426	0.0375
0.1677	5.0	450	0.1615	0.0423	0.0444	0.0407
0.1676	6.0	540	0.1615	0.0421	0.0444	0.0403
0.1682	7.0	630	0.1616	0.0394	0.0426	0.0370
0.1665	8.0	720	0.1613	0.0476	0.05	0.0458
0.1658	9.0	810	0.1610	0.0616	0.0667	0.0579
0.1674	10.0	900	0.1599	0.0987	0.1056	0.0935
0.1613	11.0	990	0.1587	0.1206	0.1278	0.1153
0.1608	12.0	1080	0.1568	0.1722	0.1796	0.1667
0.1612	13.0	1170	0.1550	0.1910	0.2019	0.1829
0.1581	14.0	1260	0.1532	0.2423	0.2537	0.2338
0.1575	15.0	1350	0.1516	0.2862	0.3	0.2759
0.1548	16.0	1440	0.1505	0.2878	0.3019	0.2773
0.1517	17.0	1530	0.1493	0.2979	0.3130	0.2866
0.1507	18.0	1620	0.1486	0.2907	0.3056	0.2796
0.1519	19.0	1710	0.1481	0.2907	0.3056	0.2796
0.1497	20.0	1800	0.1479	0.2907	0.3056	0.2796

Framework versions

• Transformers 4.50.0.dev0
• Pytorch 2.5.1+cu121
• Datasets 3.4.1
• Tokenizers 0.21.0