gena-lm-bert-base-t2t-multi_ft_BioS2_1kbpHG19_DHSs_H3K27AC

tanoManzo/gena-lm-bert-base-t2t-multi_ft_BioS2_1kbpHG19_DHSs_H3K27AC

gena-lm-bert-base-t2t-multi_ft_BioS2_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

13% of all-time downloads

All-time downloads

Public

Parameters

111M

1.3 GB 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-multi

Model card

From the Hugging Face model README

gena-lm-bert-base-t2t-multi_ft_BioS2_1kbpHG19_DHSs_H3K27AC

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: 0.4666
F1 Score: 0.8442
Precision: 0.8154
Recall: 0.8751
Accuracy: 0.8333
Auc: 0.8995
Prc: 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: 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
0.6931	0.0839	500	0.6427	0.7390	0.6242	0.9057	0.6699	0.7821	0.7840
0.6219	0.1679	1000	0.5689	0.7390	0.7963	0.6893	0.7487	0.8086	0.7935
0.5477	0.2518	1500	0.5181	0.7949	0.7556	0.8386	0.7767	0.8398	0.8123
0.5125	0.3358	2000	0.4999	0.8031	0.7565	0.8559	0.7834	0.8496	0.8161
0.4961	0.4197	2500	0.5177	0.8055	0.7647	0.8510	0.7879	0.8371	0.7976
0.4969	0.5037	3000	0.4908	0.8153	0.7495	0.8936	0.7910	0.8582	0.8306
0.4777	0.5876	3500	0.4991	0.8196	0.7549	0.8966	0.7963	0.8630	0.8307
0.4836	0.6716	4000	0.4718	0.8230	0.7577	0.9005	0.8000	0.8608	0.8324
0.4748	0.7555	4500	0.5299	0.7963	0.8009	0.7918	0.7910	0.8567	0.8069
0.4667	0.8395	5000	0.4743	0.8241	0.7622	0.8969	0.8024	0.8715	0.8450
0.4717	0.9234	5500	0.4981	0.8105	0.8091	0.8120	0.8041	0.8772	0.8542
0.4707	1.0074	6000	0.4675	0.8273	0.7656	0.8998	0.8061	0.8751	0.8371
0.459	1.0913	6500	0.4867	0.8192	0.8012	0.8380	0.8091	0.8778	0.8546
0.4544	1.1753	7000	0.4712	0.8322	0.7557	0.9258	0.8073	0.8264	0.7430
0.4324	1.2592	7500	0.4993	0.8185	0.8147	0.8224	0.8118	0.8687	0.8163
0.436	1.3432	8000	0.4777	0.8352	0.7641	0.9209	0.8125	0.8185	0.7469
0.4464	1.4271	8500	0.5148	0.8299	0.7497	0.9294	0.8034	0.8729	0.8419
0.4537	1.5111	9000	0.4503	0.8296	0.8028	0.8582	0.8180	0.8796	0.8409
0.4276	1.5950	9500	0.4540	0.8356	0.8014	0.8728	0.8227	0.8926	0.8680
0.4323	1.6790	10000	0.4512	0.8380	0.7949	0.8861	0.8232	0.8748	0.8222
0.4384	1.7629	10500	0.4724	0.8386	0.7655	0.9271	0.8158	0.8836	0.8405
0.4076	1.8469	11000	0.4626	0.8335	0.8204	0.8471	0.8254	0.8813	0.8340
0.439	1.9308	11500	0.4399	0.8443	0.7807	0.9193	0.8251	0.8888	0.8487
0.4164	2.0148	12000	0.4522	0.8437	0.7820	0.9161	0.8249	0.8940	0.8548
0.4075	2.0987	12500	0.4718	0.8417	0.8069	0.8796	0.8292	0.8962	0.8771
0.406	2.1827	13000	0.4935	0.8233	0.8442	0.8035	0.8220	0.9000	0.8729
0.3958	2.2666	13500	0.4891	0.8427	0.8172	0.8699	0.8324	0.8896	0.8443
0.4353	2.3506	14000	0.4666	0.8442	0.8154	0.8751	0.8333	0.8995	0.8745

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