gena-lm-bert-base-t2t_ft_BioS73_1kbpHG19_DHSs_H3K27AC

tanoManzo/gena-lm-bert-base-t2t_ft_BioS73_1kbpHG19_DHSs_H3K27AC

gena-lm-bert-base-t2t_ft_BioS73_1kbpHG19_DHSs_H3K27AC is a machine learning model from tanoManzo. Use it for the machine learning task on the model card, and read the license before you ship it in a product.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

11% of all-time downloads

All-time downloads

Public

Parameters

111M

443 MB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors443 MB · 100%

Parameter types

How the weights are stored.

F32111M · 100%

Base models

AIRI-Institute/gena-lm-bert-base-t2t

Model card

From the Hugging Face model README

gena-lm-bert-base-t2t_ft_BioS73_1kbpHG19_DHSs_H3K27AC

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

Loss: 0.5681
F1 Score: 0.8606
Precision: 0.8346
Recall: 0.8883
Accuracy: 0.8464
Auc: 0.9057
Prc: 0.8788

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
0.6857	0.1864	500	0.6036	0.7971	0.7225	0.8890	0.7585	0.8247	0.7929
0.5451	0.3727	1000	0.4777	0.8256	0.7793	0.8778	0.8021	0.8670	0.8418
0.4643	0.5591	1500	0.4579	0.8296	0.8228	0.8366	0.8166	0.8780	0.8550
0.4425	0.7454	2000	0.4760	0.8315	0.8307	0.8324	0.8200	0.8770	0.8551
0.4363	0.9318	2500	0.4510	0.8457	0.8088	0.8862	0.8274	0.8755	0.8489
0.4201	1.1182	3000	0.4354	0.8534	0.8062	0.9064	0.8338	0.8876	0.8626
0.4138	1.3045	3500	0.4798	0.8504	0.8004	0.9071	0.8297	0.8874	0.8611
0.4153	1.4909	4000	0.4520	0.8493	0.8177	0.8834	0.8327	0.9034	0.8996
0.3919	1.6772	4500	0.4782	0.8514	0.8192	0.8862	0.8349	0.8972	0.8699
0.3899	1.8636	5000	0.4710	0.8547	0.8058	0.9099	0.8349	0.8892	0.8532
0.3779	2.0499	5500	0.5085	0.8549	0.8151	0.8987	0.8371	0.8910	0.8629
0.4259	2.2363	6000	0.4850	0.8576	0.7992	0.9253	0.8360	0.8904	0.8549
0.3808	2.4227	6500	0.4826	0.8530	0.7793	0.9420	0.8267	0.8805	0.8371
0.3974	2.6090	7000	0.4625	0.8577	0.8101	0.9113	0.8386	0.9101	0.9002
0.3948	2.7954	7500	0.5013	0.8547	0.8243	0.8876	0.8390	0.9022	0.8830
0.3707	2.9817	8000	0.5439	0.8597	0.7881	0.9455	0.8353	0.8863	0.8461
0.3831	3.1681	8500	0.5381	0.8622	0.7938	0.9434	0.8390	0.8403	0.7716
0.3949	3.3545	9000	0.5503	0.8528	0.8219	0.8862	0.8367	0.9103	0.8892
0.405	3.5408	9500	0.5180	0.8596	0.8090	0.9169	0.8401	0.9103	0.8895
0.3759	3.7272	10000	0.5320	0.8581	0.8169	0.9036	0.8405	0.8719	0.8090
0.3821	3.9135	10500	0.5786	0.8533	0.8326	0.875	0.8394	0.8952	0.8614
0.3608	4.0999	11000	0.5681	0.8606	0.8346	0.8883	0.8464	0.9057	0.8788

Framework versions

Transformers 4.42.3
Pytorch 2.3.0+cu121
Datasets 2.18.0
Tokenizers 0.19.0

Type: bert
Created: Sep 25, 2024
Updated: Sep 25, 2024