nbbert_ED

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

• Loss: 0.9955
• F1-score: 0.8361

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	F1-score
No log	1.0	69	0.6947	0.4209
No log	2.0	138	0.8251	0.6436
No log	3.0	207	0.6215	0.7587
No log	4.0	276	0.5942	0.7622
No log	5.0	345	0.6512	0.7622
No log	6.0	414	0.5853	0.7855
No log	7.0	483	1.1781	0.6619
0.4341	8.0	552	0.9684	0.7596
0.4341	9.0	621	0.8108	0.7951
0.4341	10.0	690	0.9732	0.7849
0.4341	11.0	759	0.8429	0.8276
0.4341	12.0	828	1.1912	0.7576
0.4341	13.0	897	1.0208	0.8115
0.4341	14.0	966	0.9234	0.8197
0.1528	15.0	1035	0.8931	0.8357
0.1528	16.0	1104	1.1005	0.8025
0.1528	17.0	1173	0.9808	0.8279
0.1528	18.0	1242	1.0438	0.8195
0.1528	19.0	1311	1.0193	0.8197
0.1528	20.0	1380	0.9955	0.8361

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.0+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1