metadata
base_model: AIRI-Institute/gena-lm-bert-base-t2t-multi
tags:
- generated_from_trainer
metrics:
- f1
- accuracy
model-index:
- name: mus_promoter-finetuned-lora-bert-base-t2t-multi
results: []
mus_promoter-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: 0.0021
- F1: 1.0
- Mcc Score: 1.0
- Accuracy: 1.0
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 |
|---|---|---|---|---|---|---|
| 0.169 | 0.43 | 100 | 0.2552 | 0.9429 | 0.8814 | 0.9375 |
| 0.1379 | 0.85 | 200 | 0.2600 | 0.9600 | 0.9039 | 0.9531 |
| 0.0749 | 1.28 | 300 | 0.1726 | 0.9737 | 0.9373 | 0.9688 |
| 0.0708 | 1.71 | 400 | 0.0171 | 0.9863 | 0.9686 | 0.9844 |
| 0.0579 | 2.14 | 500 | 0.1011 | 0.9863 | 0.9686 | 0.9844 |
| 0.0512 | 2.56 | 600 | 0.0993 | 0.9722 | 0.9385 | 0.9688 |
| 0.0238 | 2.99 | 700 | 0.0065 | 1.0 | 1.0 | 1.0 |
| 0.0108 | 3.42 | 800 | 0.0605 | 0.9863 | 0.9686 | 0.9844 |
| 0.024 | 3.85 | 900 | 0.0029 | 1.0 | 1.0 | 1.0 |
| 0.0178 | 4.27 | 1000 | 0.0021 | 1.0 | 1.0 | 1.0 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.1.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2