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: 0.1792
F1: 0.9577
Mcc Score: 0.9094
Accuracy: 0.9531

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: 0.0005
train_batch_size: 8
eval_batch_size: 64
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
training_steps: 1000

Training results

Training Loss	Epoch	Step	Validation Loss	F1	Mcc Score	Accuracy
0.6514	0.43	100	0.4785	0.9351	0.8414	0.9219
0.3646	0.85	200	0.9139	0.8276	0.5429	0.7656
0.5499	1.28	300	0.2149	0.9600	0.9039	0.9531
0.3001	1.71	400	0.3707	0.9351	0.8414	0.9219
0.227	2.14	500	0.1903	0.9474	0.8724	0.9375
0.2107	2.56	600	0.1515	0.9730	0.9359	0.9688
0.1793	2.99	700	0.2371	0.9444	0.8749	0.9375
0.1212	3.42	800	0.1112	0.9600	0.9039	0.9531
0.1338	3.85	900	0.1401	0.9730	0.9359	0.9688
0.0912	4.27	1000	0.1792	0.9577	0.9094	0.9531

Framework versions

Transformers 4.37.2
Pytorch 2.1.0+cu121
Datasets 2.17.1
Tokenizers 0.15.2

LiukG/mus_promoter-finetuned-lora-bert-base-t2t

mus_promoter-finetuned-lora-bert-base-t2t

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

LiukG/
mus_promoter-finetuned-lora-bert-base-t2t