gena-lm-bert-base-t2t-multi_ft_BioS2_1kbpHG19_DHSs_H3K27AC_one_shot

This model is a fine-tuned version of AIRI-Institute/gena-lm-bert-base-t2t-multi on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.5976
• F1 Score: 0.7887
• Precision: 0.7368
• Recall: 0.8485
• Accuracy: 0.7458
• Auc: 0.7949
• Prc: 0.8250

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: 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
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	F1 Score	Precision	Recall	Accuracy	Auc	Prc
0.6969	8.3333	500	0.6487	0.7077	0.7188	0.6970	0.6780	0.7523	0.7272
0.6553	16.6667	1000	0.5976	0.7887	0.7368	0.8485	0.7458	0.7949	0.8250

Framework versions

• Transformers 4.46.0.dev0
• Pytorch 2.4.1+cu121
• Datasets 2.18.0
• Tokenizers 0.20.0