ConPlag_2_codeberta_ep30_bs16_lr1e-05_l512_s42_ppy_f_beta_score_2

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

• Loss: 0.6677
• Accuracy: 0.9197
• Recall: 0.8810
• Precision: 0.8605
• F1: 0.8706
• F Beta Score: 0.8745

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: 1e-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: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Recall	Precision	F1	F Beta Score
No log	1.0	40	0.6247	0.7372	0.6905	0.5577	0.6170	0.6433
No log	2.0	80	0.5205	0.7007	0.8333	0.5072	0.6306	0.6957
0.6216	3.0	120	0.4895	0.8467	0.5952	0.8621	0.7042	0.6579
0.6216	4.0	160	0.4377	0.8613	0.6667	0.8485	0.7467	0.7137
0.3445	5.0	200	0.4008	0.8759	0.8095	0.7907	0.8	0.8036
0.3445	6.0	240	0.3619	0.9051	0.8095	0.8718	0.8395	0.8277
0.3445	7.0	280	0.3894	0.8978	0.8095	0.85	0.8293	0.8216
0.1703	8.0	320	0.5518	0.9197	0.7857	0.9429	0.8571	0.8282
0.1703	9.0	360	0.4551	0.9197	0.8810	0.8605	0.8706	0.8745
0.0638	10.0	400	0.4796	0.9270	0.9286	0.8478	0.8864	0.9021
0.0638	11.0	440	0.5482	0.8905	0.9048	0.7755	0.8352	0.8606
0.0638	12.0	480	0.6586	0.9270	0.8810	0.8810	0.8810	0.8810
0.0324	13.0	520	0.6902	0.9270	0.8810	0.8810	0.8810	0.8810
0.0324	14.0	560	0.6943	0.9270	0.8810	0.8810	0.8810	0.8810
0.0208	15.0	600	0.6677	0.9197	0.8810	0.8605	0.8706	0.8745

Framework versions

• Transformers 4.45.2
• Pytorch 2.5.1+cu124
• Datasets 3.1.0
• Tokenizers 0.20.3