metadata

base_model: AIRI-Institute/gena-lm-bert-base-t2t-multi
tags:
  - generated_from_trainer
metrics:
  - f1
  - accuracy
model-index:
  - name: gut_1024-finetuned-lora-bert-base-t2t-multi
    results: []

gut_1024-finetuned-lora-bert-base-t2t-multi

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: 0.4764
F1: 0.8478
Mcc Score: 0.5903
Accuracy: 0.8049

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
0.7012	0.02	100	0.6683	0.7478	0.0	0.5971
0.7003	0.04	200	0.6391	0.7825	0.3306	0.6710
0.6583	0.05	300	0.6211	0.7853	0.3430	0.6778
0.6381	0.07	400	0.6512	0.7812	0.3247	0.6681
0.6438	0.09	500	0.6524	0.3380	0.1874	0.5004
0.6028	0.11	600	0.5646	0.8004	0.5013	0.7606
0.5154	0.12	700	0.5437	0.8392	0.5576	0.7884
0.5226	0.14	800	0.4823	0.8503	0.5901	0.8024
0.5104	0.16	900	0.4856	0.8452	0.5851	0.8028
0.5538	0.18	1000	0.4764	0.8478	0.5903	0.8049

Framework versions

Transformers 4.38.1
Pytorch 2.1.0+cu121
Datasets 2.17.1
Tokenizers 0.15.2