DNABERT-2-117M_ft_Hepg2_1kbpHG19_DHSs_H3K27AC

This model is a fine-tuned version of zhihan1996/DNABERT-2-117M on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.4809
• F1 Score: 0.8080
• Precision: 0.7661
• Recall: 0.8546
• Accuracy: 0.7770
• Mcc Score: 0.5487
• Roc Auc Score: 0.7686

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: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	F1 Score	Precision	Recall	Accuracy	Mcc Score	Roc Auc Score
0.4948	1.4881	500	0.5034	0.7825	0.7980	0.7677	0.7658	0.5296	0.7656
0.4623	2.9762	1000	0.4809	0.8080	0.7661	0.8546	0.7770	0.5487	0.7686

Framework versions

• Transformers 4.42.3
• Pytorch 2.3.0+cu121
• Datasets 2.18.0
• Tokenizers 0.19.0