|
|
--- |
|
|
base_model: AIRI-Institute/gena-lm-bert-large-t2t |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- f1 |
|
|
- accuracy |
|
|
model-index: |
|
|
- name: gut_1024-finetuned-lora-bert-large-t2t |
|
|
results: [] |
|
|
--- |
|
|
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
|
|
# gut_1024-finetuned-lora-bert-large-t2t |
|
|
|
|
|
This model is a fine-tuned version of [AIRI-Institute/gena-lm-bert-large-t2t](https://huggingface.co/AIRI-Institute/gena-lm-bert-large-t2t) on the None dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.4378 |
|
|
- F1: 0.8676 |
|
|
- Mcc Score: 0.6476 |
|
|
- Accuracy: 0.8315 |
|
|
|
|
|
## 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 | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:---------:|:--------:| |
|
|
| 0.6357 | 0.02 | 100 | 0.5047 | 0.8379 | 0.5616 | 0.7918 | |
|
|
| 0.5873 | 0.04 | 200 | 1.0646 | 0.6898 | 0.4070 | 0.6829 | |
|
|
| 0.5661 | 0.05 | 300 | 0.4921 | 0.8386 | 0.5593 | 0.7901 | |
|
|
| 0.5018 | 0.07 | 400 | 0.4753 | 0.8476 | 0.5791 | 0.7927 | |
|
|
| 0.5461 | 0.09 | 500 | 0.4841 | 0.8465 | 0.5947 | 0.8074 | |
|
|
| 0.4555 | 0.11 | 600 | 0.4521 | 0.8580 | 0.6239 | 0.8209 | |
|
|
| 0.4155 | 0.12 | 700 | 0.4519 | 0.8655 | 0.6386 | 0.8264 | |
|
|
| 0.438 | 0.14 | 800 | 0.4634 | 0.8539 | 0.6130 | 0.8159 | |
|
|
| 0.4306 | 0.16 | 900 | 0.4298 | 0.8615 | 0.6232 | 0.8150 | |
|
|
| 0.4791 | 0.18 | 1000 | 0.4378 | 0.8676 | 0.6476 | 0.8315 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.38.1 |
|
|
- Pytorch 2.1.0+cu121 |
|
|
- Datasets 2.17.1 |
|
|
- Tokenizers 0.15.2 |
|
|
|
